© 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. 7-RES-JB
    11. 17850
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of fabric or fabricating, sometimes used metaphorically

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of "fabric" 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
    cffffcc
    -0.89
    erey
    -0.76
    edom
    -0.73
    nikov
    -0.72
    regor
    -0.72
    aeper
    -0.68
    llan
    -0.66
    enhagen
    -0.66
    sets
    -0.66
    essor
    -0.65
    POSITIVE LOGITS
     fabric
    1.05
    ations
    0.88
     woven
    0.87
     Fabric
    0.85
     filament
    0.85
    ator
    0.84
     weave
    0.84
    acies
    0.82
    adoes
    0.82
     fabrication
    0.82
    Activations Density 0.025%

    No Known Activations