© 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. 0-RES-JB
    6. 6842
    Prev
    Next
    INDEX
    Explanations

    adjectives indicating high level of competence or eligibility

    oai_token-act-pair · gpt-3.5-turbo

    the word "qualified" in various contexts related to competency or suitability for a role

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    angles
    -0.71
    eye
    -0.67
    hide
    -0.67
     Sentinel
    -0.67
    Angelo
    -0.64
    mes
    -0.64
     invis
    -0.64
     Travels
    -0.64
     havoc
    -0.63
    sie
    -0.62
    POSITIVE LOGITS
     qualified
    4.00
    qualified
    2.65
     qualifying
    1.88
     Qual
    1.86
     qualify
    1.80
    Qual
    1.75
     qualification
    1.58
     qualifies
    1.52
     competent
    1.48
     eligible
    1.47
    Activations Density 0.007%

    No Known Activations