© 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. 4-RES-JB
    11. 6012
    Prev
    Next
    INDEX
    Explanations

    locations

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "place."

    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
    igans
    -0.67
    quel
    -0.66
    CHAT
    -0.65
    agascar
    -0.65
    rd
    -0.64
    irl
    -0.62
    umin
    -0.61
    olyn
    -0.60
    jin
    -0.60
    archives
    -0.60
    POSITIVE LOGITS
    holder
    1.14
    holders
    1.08
    bos
    1.05
    ername
    0.89
    upon
    0.79
    knife
    0.78
    bo
    0.78
    ngth
    0.73
     Temperature
    0.69
    down
    0.69
    Activations Density 0.032%

    No Known Activations