© 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. 2-RES-JB
    11. 23162
    Prev
    Next
    INDEX
    Explanations

    locations or pathways presented in a document, especially ones described as long, wide, or stretching between specific areas

    oai_token-act-pair · gpt-3.5-turbo

    references to corridors in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itsu
    -0.74
    iak
    -0.72
    held
    -0.68
    orah
    -0.67
    omi
    -0.67
    mol
    -0.67
    odium
    -0.66
    ucks
    -0.66
    itude
    -0.66
    ás
    -0.66
    POSITIVE LOGITS
     corridors
    1.30
     corridor
    1.19
     Corridor
    1.17
    ridor
    1.08
     routes
    0.87
     passages
    0.85
    ttes
    0.84
     segments
    0.82
     route
    0.81
    ways
    0.80
    Activations Density 0.007%

    No Known Activations