© 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. 1-RES-JB
    6. 5560
    Prev
    Next
    INDEX
    Explanations

    adjectives describing a close and tenacious attachment, particularly related to physical clinging or adherence

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of clinging or attachment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rounding
    -0.69
    ACTED
    -0.68
    NAT
    -0.68
     istg
    -0.66
    ICAN
    -0.65
    Ô
    -0.64
    brance
    -0.64
    Scotland
    -0.63
    OTT
    -0.62
     è£ıç
    -0.62
    POSITIVE LOGITS
     cling
    1.41
     clinging
    1.05
     welf
    0.84
    iness
    0.80
     pigeon
    0.80
    rily
    0.80
     nodd
    0.80
     adolesc
    0.79
    ueless
    0.75
    ModLoader
    0.75
    Activations Density 0.007%

    No Known Activations