© 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. 8-RES-JB
    11. 20315
    Prev
    Next
    INDEX
    Explanations

    words related to various activities and objects

    oai_token-act-pair · gpt-3.5-turbo

    references to performance art and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Latest
    -0.70
     §§
    -0.70
     Hots
    -0.67
     Sect
    -0.63
     Indra
    -0.61
     Legislative
    -0.60
     Sections
    -0.59
     Ones
    -0.59
     Ancients
    -0.59
     Robots
    -0.58
    POSITIVE LOGITS
    less
    0.87
    able
    0.84
     breaker
    0.81
    breaker
    0.71
     worthy
    0.71
     filler
    0.68
     standpoint
    0.68
     runner
    0.67
     deterrent
    0.67
     cutter
    0.65
    Activations Density 0.663%

    No Known Activations