© 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. 9-RES-JB
    11. 5351
    Prev
    Next
    INDEX
    Explanations

    proper nouns that are likely related to media, entertainment, or other cultural references

    oai_token-act-pair · gpt-3.5-turbo

    uppercase letters or initials typically used in titles and names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è£ħ
    -0.68
    lessly
    -0.66
    matically
    -0.64
     publicly
    -0.62
    efully
    -0.61
    itatively
    -0.60
    staking
    -0.59
     permitting
    -0.59
     effic
    -0.59
     explanatory
    -0.58
    POSITIVE LOGITS
    ombat
    0.99
    atoes
    0.91
    angles
    0.84
    utions
    0.83
    izons
    0.80
    clerosis
    0.79
    itudes
    0.78
    idays
    0.78
    apes
    0.78
    ipers
    0.78
    Activations Density 0.244%

    No Known Activations