© 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. 2-RES-JB
    11. 9420
    Prev
    Next
    INDEX
    Explanations

    references to a person named "Robinson" or phrases related to the name

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Robinson."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ablishment
    -0.86
    ropolitan
    -0.79
    uate
    -0.78
    SEE
    -0.74
    erest
    -0.70
    umbers
    -0.69
    ulhu
    -0.69
    uated
    -0.68
    WAYS
    -0.68
    ibal
    -0.68
    POSITIVE LOGITS
     Crus
    1.08
    inson
    1.05
     Robinson
    0.94
     Sapp
    0.71
    bie
    0.67
    hurst
    0.66
     Mansion
    0.66
    otics
    0.64
     Hub
    0.63
     Cookies
    0.63
    Activations Density 0.009%

    No Known Activations