© 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. 10-RES-JB
    11. 6901
    Prev
    Next
    INDEX
    Explanations

    phrases indicating causation or consequences

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating causation or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atching
    -0.63
    ointed
    -0.56
    cup
    -0.55
     rivalry
    -0.54
    schild
    -0.54
    osal
    -0.53
    pec
    -0.52
    ãĥĩãĤ£
    -0.52
    ature
    -0.52
     squared
    -0.51
    POSITIVE LOGITS
     to
    1.09
     nowhere
    0.98
     inevitably
    0.97
     inex
    0.91
     toward
    0.86
     towards
    0.81
     us
    0.80
    entious
    0.79
     thereto
    0.78
     into
    0.76
    Activations Density 0.040%

    No Known Activations