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. 2-RES-JB
    6. 69
    Prev
    Next
    INDEX
    Explanations

    It appears that Neuron 4 did not activate for any of the words provided in the document segments; therefore, no pattern of interest can be identified based on the given information

    oai_token-act-pair · gpt-4-turbo
    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
    Pitt
    -0.71
    ————————————————
    -0.65
     Worcester
    -0.65
    fall
    -0.64
     Hallow
    -0.62
    Gaza
    -0.60
    violent
    -0.60
    00000000
    -0.59
    Buff
    -0.59
     Mü
    -0.58
    POSITIVE LOGITS
    ibaba
    0.96
    llular
    0.78
    llah
    0.75
    orney
    0.74
    kinson
    0.73
    ynthesis
    0.73
    inki
    0.72
    ilton
    0.67
    velength
    0.66
    oya
    0.66
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.