© 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. 4-RES-JB
    6. 9076
    Prev
    Next
    INDEX
    Explanations

    actions related to physically holding onto something tightly

    oai_token-act-pair · gpt-3.5-turbo

    forms of the word "cling" and related actions of grasping or holding onto something

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

    No Comments

    Negative Logits
     rounding
    -0.69
    ACTED
    -0.68
    ufact
    -0.66
    ordan
    -0.66
    brance
    -0.66
     è£ıç
    -0.65
    BLIC
    -0.64
    rawdownloadcloneembedreportprint
    -0.62
    ICAN
    -0.61
    Eth
    -0.60
    POSITIVE LOGITS
     cling
    1.32
     clinging
    0.98
    rily
    0.91
    iness
    0.83
     pigeon
    0.80
    byss
    0.77
    odge
    0.73
     confinement
    0.73
    ingly
    0.72
    holders
    0.72
    Activations Density 0.015%

    No Known Activations