© 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. 7008
    Prev
    Next
    INDEX
    Explanations

    commands or requests in the form of "Give X"

    oai_token-act-pair · gpt-3.5-turbo

    commands or requests for action

    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
    éĹ
    -0.74
    cffffcc
    -0.71
    ITE
    -0.65
    ELF
    -0.63
     constitu
    -0.60
     SERVICE
    -0.60
    */(
    -0.60
     record
    -0.58
    PATH
    -0.58
    mith
    -0.58
    POSITIVE LOGITS
     Yourself
    0.97
    ings
    0.96
     yourselves
    0.88
     Your
    0.84
    ership
    0.83
    resa
    0.83
     Them
    0.81
    nces
    0.77
    ments
    0.76
    ables
    0.74
    Activations Density 0.170%

    No Known Activations