© 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. 4-RES-JB
    11. 7358
    Prev
    Next
    INDEX
    Explanations

    verbs related to planning or intentions

    oai_token-act-pair · gpt-3.5-turbo

    gerunds or present participles that indicate ongoing actions or states

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

    No Comments

    Negative Logits
    fortunately
    -0.68
     alike
    -0.66
    played
    -0.61
     holder
    -0.61
    si
    -0.60
    aligned
    -0.60
    imposed
    -0.60
     doubtless
    -0.59
     Audi
    -0.58
    ersen
    -0.58
    POSITIVE LOGITS
     oneself
    0.80
     Pengu
    0.72
    AMES
    0.68
    BAT
    0.68
    BuyableInstoreAndOnline
    0.66
     Volunte
    0.65
    ãĥ¼ãĥĨ
    0.65
     Yourself
    0.63
    illet
    0.63
     INTO
    0.63
    Activations Density 0.405%

    No Known Activations