© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 8873
    Prev
    Next
    INDEX
    Explanations

    words related to journalism and news analysis, including names of journalists and news programs

    oai_token-act-pair · gpt-3.5-turbo

    instances of dialogue or speech in a context, particularly from a news or interview format

    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
    ealous
    -0.84
    CONCLUS
    -0.71
    uton
    -0.68
    oi
    -0.68
    lol
    -0.67
    Ws
    -0.67
    ahon
    -0.66
    [/
    -0.66
     OC
    -0.66
     ."
    -0.66
    POSITIVE LOGITS
     NPR
    1.19
     Transcript
    0.94
     VIDE
    0.93
    NPR
    0.91
     Explain
    0.89
     Democracy
    0.87
     Congressman
    0.84
     GOODMAN
    0.84
     joins
    0.79
    toggle
    0.76
    Activations Density 0.230%

    No Known Activations