© 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. 0-RES-JB
    11. 20349
    Prev
    Next
    INDEX
    Explanations

    words related to natural wood materials

    oai_token-act-pair · gpt-3.5-turbo

    mentions of wood and timber

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Factor
    -0.78
     Immunity
    -0.69
    CLASSIFIED
    -0.66
    oppable
    -0.66
    GROUP
    -0.66
    AIDS
    -0.66
     Saban
    -0.65
    actionDate
    -0.65
    EGA
    -0.65
    Reloaded
    -0.65
    POSITIVE LOGITS
     wood
    3.48
     timber
    2.05
    Wood
    2.00
     Wood
    1.97
     woods
    1.91
    wood
    1.86
     oak
    1.86
     wooden
    1.75
     lumber
    1.74
     woodland
    1.59
    Activations Density 0.008%

    No Known Activations