© 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. 2-RES-JB
    11. 23410
    Prev
    Next
    INDEX
    Explanations

    words related to affordability and being unaffiliated

    oai_token-act-pair · gpt-3.5-turbo

    terms related to affordability and being unaffiliated

    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
     Cellular
    -0.75
    MQ
    -0.74
    senal
    -0.73
    culosis
    -0.71
     Logic
    -0.68
    Reviewer
    -0.68
     Tone
    -0.67
     Muller
    -0.63
     Rutherford
    -0.63
     Principal
    -0.63
    POSITIVE LOGITS
    ordable
    1.30
     unaff
    1.13
    iliated
    1.05
    licted
    0.97
    abled
    0.83
     affordability
    0.83
    erving
    0.83
    alus
    0.82
    erved
    0.80
    licts
    0.80
    Activations Density 0.007%

    No Known Activations