© 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. 7-RES-JB
    11. 2700
    Prev
    Next
    INDEX
    Explanations

    words related to value or importance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "valuable" and its contextual usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilk
    -0.81
    bands
    -0.81
    annis
    -0.80
    ulhu
    -0.78
    abad
    -0.76
    abi
    -0.76
    alis
    -0.75
    imposed
    -0.72
    central
    -0.71
    abel
    -0.70
    POSITIVE LOGITS
     asset
    1.01
     valuable
    0.96
     trove
    0.89
     possessions
    0.84
     lessons
    0.83
     consideration
    0.82
     insight
    0.80
     priceless
    0.79
     commodity
    0.78
     contribution
    0.77
    Activations Density 0.050%

    No Known Activations