© 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. 6-RES-JB
    11. 19769
    Prev
    Next
    INDEX
    Explanations

    phrases related to governmental or political actions

    oai_token-act-pair · gpt-3.5-turbo

    components or elements that signify uncertainty or ambiguity in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    —"
    -0.55
     Ethernet
    -0.55
    enger
    -0.54
    iste
    -0.54
     Brewery
    -0.54
     DevOnline
    -0.53
     IPA
    -0.53
     café
    -0.51
    estones
    -0.50
     naming
    -0.50
    POSITIVE LOGITS
    widget
    0.59
    maxwell
    0.58
    etheless
    0.57
    ↵Âł
    0.56
     grate
    0.56
    consider
    0.54
    ↵↵
    0.53
     dont
    0.52
     david
    0.52
    ãħĭãħĭ
    0.52
    Activations Density 0.972%

    No Known Activations