© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 22442
    Prev
    Next
    INDEX
    Explanations

    words related to feelings of helplessness and hopelessness

    oai_token-act-pair · gpt-3.5-turbo

    expressions of helplessness and hopelessness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ULT
    -0.74
    APH
    -0.71
    Downloadha
    -0.69
    ioxide
    -0.69
    代
    -0.66
    illon
    -0.66
    ucc
    -0.66
    76561
    -0.64
    itamin
    -0.64
    OTOS
    -0.64
    POSITIVE LOGITS
    ness
    2.75
    nesses
    2.27
    ly
    1.62
    NESS
    1.60
    ity
    1.25
    liness
    1.17
    itude
    1.01
    cies
    1.00
    edly
    1.00
    LY
    1.00
    Activations Density 0.131%

    No Known Activations