© 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. 3939
    Prev
    Next
    INDEX
    Explanations

    objects, places, or entities with the word "pen" in them

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "pen" in various contexts

    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
    enance
    -0.77
    ndum
    -0.70
    tt
    -0.69
     Marxism
    -0.65
    OST
    -0.62
     Athe
    -0.59
    @@@@
    -0.58
     Giuliani
    -0.57
     Fundamental
    -0.57
     Normandy
    -0.57
    POSITIVE LOGITS
    itent
    1.54
    ultimate
    1.53
    cil
    1.44
    insula
    1.30
    elope
    1.30
    alties
    1.27
    manship
    1.18
    nington
    1.10
    cill
    1.06
    ryn
    1.01
    Activations Density 0.042%

    No Known Activations