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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9-RES-JB
    6. 21455
    Prev
    Next
    INDEX
    Explanations

    phrases related to transactions or actions carried out on behalf of others

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "on" or similar prepositions indicating specific actions or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rament
    -0.72
    rors
    -0.69
    oola
    -0.62
     Protector
    -0.62
    bour
    -0.61
     Bullets
    -0.61
    wine
    -0.61
    #$
    -0.60
    otle
    -0.58
    ults
    -0.58
    POSITIVE LOGITS
     behalf
    1.96
    site
    1.16
    shore
    1.15
    etime
    1.13
    erous
    1.10
     basis
    1.07
     occasion
    1.05
    eworld
    0.99
     occasions
    0.97
     purpose
    0.96
    Activations Density 0.276%

    No Known Activations