Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 487
    Prev
    Next
    INDEX
    Explanations

    the adjective "weak"

    oai_token-act-pair · gpt-4-turbo

    words related to weakness or lack of strength

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "weak" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ittee
    -0.75
    ICAN
    -0.74
    APH
    -0.72
    agher
    -0.71
    OGR
    -0.69
    illon
    -0.68
    utical
    -0.67
    Mill
    -0.67
    rea
    -0.66
    andise
    -0.66
    POSITIVE LOGITS
    nesses
    1.13
     weak
    0.99
    lings
    0.94
    ens
    0.88
     weakest
    0.87
    ening
    0.84
    est
    0.82
    ened
    0.80
    ener
    0.77
     equival
    0.75
    Activations Density 0.008%

    No Known Activations