© 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. 6-RES-JB
    11. 19719
    Prev
    Next
    INDEX
    Explanations

    adjectives describing a high level of skill or proficiency

    oai_token-act-pair · gpt-3.5-turbo

    synonyms for skills and abilities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ITNESS
    -0.73
     ali
    -0.67
    atomic
    -0.66
    ãģŁ
    -0.65
    Reference
    -0.64
    Variable
    -0.62
    onomous
    -0.61
    orno
    -0.61
    Physical
    -0.60
    Vari
    -0.60
    POSITIVE LOGITS
     notwithstanding
    0.73
    luck
    0.71
    itism
    0.68
    iness
    0.68
    lessly
    0.68
    frey
    0.67
    cles
    0.67
     attendant
    0.67
    earances
    0.65
     eh
    0.65
    Activations Density 0.437%

    No Known Activations