© 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. 13008
    Prev
    Next
    INDEX
    Explanations

    phrases related to negative outcomes or consequences

    oai_token-act-pair · gpt-3.5-turbo

    the past participle forms of verbs

    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
     compress
    -0.69
     relocation
    -0.66
     hiber
    -0.66
     crunch
    -0.65
     withdrawal
    -0.65
     prediction
    -0.65
     Maid
    -0.63
     annexation
    -0.63
     metic
    -0.62
     limp
    -0.62
    POSITIVE LOGITS
    aught
    1.02
    lain
    0.86
    minded
    0.85
    erer
    0.85
    baugh
    0.85
    alone
    0.85
    rings
    0.78
    erers
    0.78
    unes
    0.78
    rying
    0.78
    Activations Density 0.026%

    No Known Activations