© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 17232
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressing support or being supportive towards others

    oai_token-act-pair · gpt-3.5-turbo

    mentions of supportiveness and receptiveness towards individuals or groups

    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
    hid
    -0.72
    buck
    -0.70
    ixtape
    -0.68
    angler
    -0.68
    iphate
    -0.68
    hunt
    -0.67
    Tes
    -0.66
    hung
    -0.66
    hig
    -0.66
    hun
    -0.65
    POSITIVE LOGITS
     enough
    0.88
    wcsstore
    0.85
     supportive
    0.83
     Supports
    0.75
    heses
    0.74
     minded
    0.74
    hetical
    0.74
    ative
    0.73
     affirm
    0.70
     embrace
    0.70
    Activations Density 0.021%

    No Known Activations