© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 1994
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific geographic locations or proper nouns, particularly related to places

    oai_token-act-pair · gpt-3.5-turbo

    the term "ap" in various contexts, indicating a focus on a specific entity or concept associated with that term

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     phyl
    -0.72
     explan
    -0.71
     Monstrous
    -0.70
     defic
    -0.69
     Masquerade
    -0.64
    âĸ¬âĸ¬
    -0.63
     obser
    -0.63
     Leia
    -0.62
     disapp
    -0.62
     interf
    -0.60
    POSITIVE LOGITS
    olitan
    1.40
    oleon
    1.37
    ocalypse
    1.22
    ropri
    1.19
    ocalyptic
    1.14
    rison
    1.11
    onent
    1.10
    olitics
    1.10
    osite
    1.07
    artment
    1.03
    Activations Density 0.041%

    No Known Activations