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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3953
    Prev
    Next
    INDEX
    Explanations

    words related to competition or comparison with a high emphasis on "comp"

    oai_token-act-pair · gpt-3.5-turbo

    words and root forms related to competence or competitive qualities

    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
    ################
    -0.66
     Lans
    -0.66
    ħĭ
    -0.66
     Borough
    -0.66
     Poles
    -0.65
    vae
    -0.64
     caution
    -0.64
    Downloadha
    -0.63
    hao
    -0.62
     Mens
    -0.62
    POSITIVE LOGITS
    assion
    1.24
    ensation
    1.22
    endium
    1.20
    etitive
    1.17
    rehens
    1.12
    ound
    1.12
    etition
    1.08
    artment
    1.07
    rehensive
    1.06
    ressor
    1.06
    Activations Density 0.010%

    No Known Activations