© 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. 3-RES-JB
    11. 22766
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to segments or sections within a context

    oai_token-act-pair · gpt-3.5-turbo

    references to various segments in a content or media discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CHA
    -0.72
     brink
    -0.65
     opio
    -0.64
    cia
    -0.63
     realism
    -0.62
     drafting
    -0.60
     IMAGES
    -0.60
     mother
    -0.60
     fists
    -0.58
    kens
    -0.57
    POSITIVE LOGITS
    ation
    0.98
    arily
    0.87
    ially
    0.87
    ated
    0.86
    eston
    0.84
     segments
    0.81
    ials
    0.81
    regate
    0.80
    ational
    0.80
    igr
    0.80
    Activations Density 0.010%

    No Known Activations