© 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. 24367
    Prev
    Next
    INDEX
    Explanations

    actions related to setting up or modifying settings through coding (especially in a GUI or with specific syntax)

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "in" and its various contexts

    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
    CLASSIFIED
    -0.76
    HAEL
    -0.74
     whistleblowers
    -0.70
     ens
    -0.68
     incumb
    -0.68
    llor
    -0.67
    NOW
    -0.67
    guyen
    -0.65
    irl
    -0.65
    ided
    -0.64
    POSITIVE LOGITS
     lieu
    1.34
     conjunction
    1.29
     accordance
    1.23
     addition
    1.16
    animate
    1.14
     relation
    1.10
    clusions
    1.10
     unison
    1.09
    ordinate
    1.07
     order
    1.03
    Activations Density 0.320%

    No Known Activations