© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 21508
    Prev
    Next
    INDEX
    Explanations

    words related to things that draw interest or attention, such as attractions or attractive qualities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to attractions, especially in tourist contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dat
    -0.75
     Pastebin
    -0.73
     hacked
    -0.72
    Conn
    -0.66
    DN
    -0.65
    eg
    -0.64
    dot
    -0.63
     sock
    -0.62
    neck
    -0.62
    comm
    -0.62
    POSITIVE LOGITS
     attraction
    4.01
     attractions
    3.30
     attractiveness
    1.40
     amusement
    1.37
     attracted
    1.33
     attract
    1.29
     attracts
    1.29
     attracting
    1.26
     lure
    1.25
     fascination
    1.15
    Activations Density 0.015%

    No Known Activations