© 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. 9-RES-JB
    11. 1569
    Prev
    Next
    INDEX
    Explanations

    geological or physical materials and conditions

    oai_token-act-pair · gpt-3.5-turbo

    various nouns and terms related to physical objects, conditions, and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ealous
    -0.69
    ãĤ¤
    -0.69
    orthern
    -0.66
    verning
    -0.66
    PDATE
    -0.65
    lite
    -0.65
    dependent
    -0.65
    ophob
    -0.64
    natureconservancy
    -0.64
    playing
    -0.63
    POSITIVE LOGITS
     syndrome
    1.11
     Syndrome
    0.86
    atoes
    0.72
     (%
    0.68
     (>
    0.68
     corpses
    0.65
    amples
    0.63
     corpse
    0.63
     segments
    0.63
    agram
    0.63
    Activations Density 0.581%

    No Known Activations