© 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. 6-RES-JB
    6. 23765
    Prev
    Next
    INDEX
    Explanations

    references to locations, particularly places with the word "Glen" and "Fenway" in their names

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names or terms, particularly related to notable individuals and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eering
    -0.86
     ItemLevel
    -0.66
     Overs
    -0.60
     HAM
    -0.59
     iP
    -0.57
     Lovecraft
    -0.57
     Armageddon
    -0.57
     Zed
    -0.57
     Addiction
    -0.56
     NX
    -0.56
    POSITIVE LOGITS
    olithic
    0.90
    olith
    0.86
    itent
    0.85
    kered
    0.85
    nec
    0.84
    akra
    0.83
    vironment
    0.82
    asio
    0.81
    imore
    0.80
    ilee
    0.76
    Activations Density 0.074%

    No Known Activations