© 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. 2-RES-JB
    11. 4294
    Prev
    Next
    INDEX
    Explanations

    terms related to close relationships or proximity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "close."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NZ
    -0.81
    ICAN
    -0.74
    Sov
    -0.72
     Lov
    -0.68
    CAN
    -0.65
    heim
    -0.65
    ãĥĨãĤ£
    -0.65
    天
    -0.65
    reme
    -0.65
     Peb
    -0.64
    POSITIVE LOGITS
     proximity
    0.98
     confinement
    0.91
     close
    0.84
     minded
    0.82
     deadlines
    0.78
     ties
    0.78
     confid
    0.77
     enough
    0.76
     resemblance
    0.74
     doors
    0.72
    Activations Density 0.018%

    No Known Activations