Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 6711
    Prev
    Next
    INDEX
    Explanations

    phrases related to reporting news events

    oai_token-act-pair · gpt-3.5-turbo

    statements related to incidents and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olkien
    -0.69
    ilibrium
    -0.65
     philosophers
    -0.65
     theoret
    -0.63
    iosyncr
    -0.63
     Slate
    -0.62
     theorist
    -0.62
    omics
    -0.59
    roleum
    -0.58
     Keynes
    -0.58
    POSITIVE LOGITS
    sic
    0.90
     RCMP
    0.84
    police
    0.84
    Prosecut
    0.83
    Alert
    0.81
    Police
    0.81
    Investigators
    0.79
     custody
    0.78
    Emergency
    0.75
    Charges
    0.75
    Activations Density 2.569%

    No Known Activations