© 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. 8-RES-JB
    6. 152
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of companies, states, and individuals

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "The"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ����
    -0.80
    thood
    -0.77
    etsy
    -0.76
    earch
    -0.76
    eno
    -0.74
    poke
    -0.71
    perse
    -0.67
    Ò
    -0.67
    leeve
    -0.66
    ccoli
    -0.66
    POSITIVE LOGITS
     latter
    1.51
    oret
    1.50
     result
    1.25
     implication
    1.25
     resulting
    1.21
     resultant
    1.16
     remainder
    1.13
     downside
    1.13
     ensuing
    1.12
     gist
    1.11
    Activations Density 0.330%

    No Known Activations