© 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. 13086
    Prev
    Next
    INDEX
    Explanations

    words related to objectivity and interaction

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various forms of "activity" or "interactivity."

    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
     abduct
    -0.67
    ergy
    -0.65
    Adult
    -0.61
    mine
    -0.60
     abduction
    -0.60
     VC
    -0.59
    umm
    -0.59
    VIS
    -0.59
    awar
    -0.58
    inav
    -0.58
    POSITIVE LOGITS
    yip
    1.01
    ivity
    0.98
    ativity
    0.89
     Pwr
    0.88
    ï¸
    0.85
    eous
    0.85
    ivities
    0.83
    terness
    0.82
    é¾įå¥ij士
    0.80
    gregation
    0.78
    Activations Density 0.028%

    No Known Activations