© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 14036
    Prev
    Next
    INDEX
    Explanations

    words related to rocks or rock-related activities

    oai_token-act-pair · gpt-3.5-turbo

    references to "rock" and its various contexts, including both physical objects and metaphorical uses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ufact
    -0.98
    ples
    -0.76
    uthor
    -0.72
    rha
    -0.68
    xus
    -0.68
    rification
    -0.66
     Toll
    -0.66
    oresc
    -0.66
    ienced
    -0.65
    ately
    -0.65
    POSITIVE LOGITS
    castle
    0.98
    er
    0.93
    ers
    0.91
    lake
    0.83
     formations
    0.83
     climbers
    0.82
    papers
    0.81
    paper
    0.79
    ppelin
    0.79
    stead
    0.79
    Activations Density 0.017%

    No Known Activations