© 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. 7-RES-JB
    6. 18696
    Prev
    Next
    INDEX
    Explanations

    codes or symbols like Ã, Ħ, Ĵ, Ŀ, Ă´

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names or entities

    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
    CVE
    -0.67
    geries
    -0.63
     hawk
    -0.62
     therap
    -0.61
     occas
    -0.57
     contrace
    -0.57
     tremend
    -0.57
     Crusher
    -0.57
     encount
    -0.57
    ukong
    -0.57
    POSITIVE LOGITS
    Ö¼
    0.92
    ̶
    0.89
    rique
    0.84
    ledged
    0.81
    Ïī
    0.77
    Í
    0.77
    anamo
    0.76
    âķIJâķIJ
    0.75
    Ì
    0.74
     istg
    0.72
    Activations Density 0.159%

    No Known Activations