© 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. 4039
    Prev
    Next
    INDEX
    Explanations

    information related to investigations and revelations involving government agencies and officials

    oai_token-act-pair · gpt-3.5-turbo

    references to leaked information and scandals involving political entities

    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
     ç¥ŀ
    -0.91
    ahime
    -0.88
    iku
    -0.86
     âĺ
    -0.79
     :(
    -0.76
     Languages
    -0.76
     Happiness
    -0.72
    enment
    -0.72
    ciation
    -0.71
     å¤
    -0.71
    POSITIVE LOGITS
     incrim
    1.27
     FBI
    1.26
    FBI
    1.24
     wiret
    1.19
     prosecut
    1.13
     subpoen
    1.11
     dossier
    1.11
     investigative
    1.07
     intelligence
    1.06
     informant
    1.05
    Activations Density 1.505%

    No Known Activations