© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 9542
    Prev
    Next
    INDEX
    Explanations

    verbs or phrases related to actions or functionalities

    oai_token-act-pair · gpt-3.5-turbo

    actionable verbs indicating processes or functions

    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
    thren
    -0.64
    swick
    -0.63
     bour
    -0.62
    conn
    -0.61
    uds
    -0.61
    bow
    -0.60
    atre
    -0.59
     That
    -0.59
    col
    -0.58
    ricks
    -0.58
    POSITIVE LOGITS
    é¾įå¥ij士
    0.72
    auna
    0.70
     passers
    0.69
    ema
    0.65
     Brach
    0.60
    ancies
    0.60
     interoper
    0.59
    ļéĨĴ
    0.59
    lando
    0.59
    annot
    0.58
    Activations Density 0.310%

    No Known Activations