© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 10932
    Prev
    Next
    INDEX
    Explanations

    phrases related to the Chelsea football/soccer club

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the football club Chelsea

    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
    haar
    -0.81
    utm
    -0.71
    ommel
    -0.69
    lopp
    -0.69
    laus
    -0.68
    lying
    -0.68
    rm
    -0.68
    oppable
    -0.67
    paio
    -0.67
    Rand
    -0.66
    POSITIVE LOGITS
     Handler
    1.02
     Harbour
    0.83
     Manning
    0.80
     FC
    0.76
     ABE
    0.70
    Leaks
    0.69
     flats
    0.69
    bies
    0.67
     Nationals
    0.67
     Deposit
    0.67
    Activations Density 0.013%

    No Known Activations