© 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. 7-RES-JB
    11. 8522
    Prev
    Next
    INDEX
    Explanations

    individuals or entities that are part of a group or assembly

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference lists of people or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bis
    -0.82
     guiActiveUnfocused
    -0.74
    ahime
    -0.74
    ciation
    -0.72
    ories
    -0.72
    Scale
    -0.71
    ipple
    -0.67
    Style
    -0.67
    obal
    -0.65
    fw
    -0.65
    POSITIVE LOGITS
     representatives
    0.96
     Jehovah
    0.91
     elderly
    0.91
     Mohamed
    0.86
     Vincent
    0.86
     fellow
    0.85
     Ahmad
    0.85
     Mohammad
    0.84
     retirees
    0.84
     Gina
    0.84
    Activations Density 0.489%

    No Known Activations