© 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. 11-RES-JB
    11. 9895
    Prev
    Next
    INDEX
    Explanations

    phrases related to travel and companionship

    oai_token-act-pair · gpt-3.5-turbo

    references to martial arts and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odus
    -0.79
    uter
    -0.73
    caps
    -0.63
    uckland
    -0.63
    olation
    -0.63
     DH
    -0.62
    ut
    -0.61
    ified
    -0.60
    uture
    -0.60
     Dy
    -0.59
    POSITIVE LOGITS
     spirits
    0.93
     spirit
    0.87
     arts
    0.86
     artists
    0.81
    spir
    0.74
     motives
    0.72
     herbs
    0.72
     artist
    0.68
     intent
    0.66
     ausp
    0.66
    Activations Density 0.129%

    No Known Activations