Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 3676
    Prev
    Next
    INDEX
    Explanations

    names and possibly keywords related to criminal cases or news events

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals or proper nouns, particularly those with high activation values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    essee
    -0.72
    ACTED
    -0.72
    Constructed
    -0.70
    ropri
    -0.70
    ffic
    -0.69
    NetMessage
    -0.66
    uncture
    -0.65
    ossession
    -0.64
    ventus
    -0.64
     Sacrament
    -0.64
    POSITIVE LOGITS
    renheit
    1.08
     Wah
    1.04
     Zah
    0.99
    ttp
    0.94
    awk
    0.94
    aji
    0.94
    rite
    0.92
    tml
    0.89
    ls
    0.89
    IJ
    0.87
    Activations Density 0.008%

    No Known Activations