© 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. 21270
    Prev
    Next
    INDEX
    Explanations

    references to cages and enclosures

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "cage" in various contexts

    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
    IELD
    -0.73
    ACTED
    -0.71
     Bundes
    -0.70
     Nare
    -0.67
    inoa
    -0.65
     Fargo
    -0.65
    igate
    -0.65
    ibel
    -0.63
     lender
    -0.61
    atio
    -0.61
    POSITIVE LOGITS
    door
    1.00
     cage
    0.98
     cages
    0.94
    hold
    0.84
     Cage
    0.83
    pit
    0.81
    washer
    0.78
    doors
    0.74
    mong
    0.71
    mates
    0.71
    Activations Density 0.050%

    No Known Activations