© 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. 4-RES-JB
    11. 15219
    Prev
    Next
    INDEX
    Explanations

    phrases related to broadcasting and news reporting

    oai_token-act-pair · gpt-3.5-turbo

    references to broadcasters in various contexts

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

    No Comments

    Negative Logits
    illard
    -0.93
    hots
    -0.72
    eanor
    -0.68
    ente
    -0.66
    ential
    -0.64
    ortium
    -0.64
    hiro
    -0.64
    BuyableInstoreAndOnline
    -0.64
    istries
    -0.63
    plets
    -0.63
    POSITIVE LOGITS
     broadcaster
    1.17
     broadcasters
    0.94
    caster
    0.91
    levision
    0.91
    casters
    0.88
     Broadcasting
    0.82
     Broadcast
    0.77
    trop
    0.76
     broadcasting
    0.74
     announcer
    0.74
    Activations Density 0.007%

    No Known Activations