© 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. 912
    Prev
    Next
    INDEX
    Explanations

    the acronym "CBS" within the document

    oai_token-act-pair · gpt-4-turbo

    mentions related to news networks, especially "CBS"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the CBS network

    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
    arist
    -0.86
    aced
    -0.86
    agnar
    -0.81
    yip
    -0.78
    antics
    -0.76
    haps
    -0.76
     inval
    -0.73
    afort
    -0.72
    ances
    -0.72
    rors
    -0.72
    POSITIVE LOGITS
    CBS
    1.06
    DAQ
    1.01
    IRO
    0.94
    CI
    0.91
    DF
    0.89
    NEWS
    0.85
    ANE
    0.84
     Evening
    0.83
    LINE
    0.82
    EW
    0.82
    Activations Density 0.007%

    No Known Activations