© 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. 8-RES-JB
    11. 15172
    Prev
    Next
    INDEX
    Explanations

    mentions of the company "HP" and related terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the brand "HP."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Interstitial
    -0.80
    taboola
    -0.74
    notations
    -0.72
    horn
    -0.70
     thirds
    -0.68
    coni
    -0.66
    âĶģ
    -0.65
     whist
    -0.65
    oshenko
    -0.65
    soDeliveryDate
    -0.63
    POSITIVE LOGITS
     Lovecraft
    1.23
     Pavilion
    1.02
    ilipp
    0.85
    rint
    0.80
    erity
    0.79
    oenix
    0.78
    ython
    0.77
    HP
    0.76
    ADA
    0.72
    LC
    0.72
    Activations Density 0.036%

    No Known Activations