© 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. 17713
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences ending with punctuation like period or comma followed by a high emotion word

    oai_token-act-pair · gpt-3.5-turbo

    punctuation indicating the end of statements or sentences

    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
    iden
    -0.69
    ighed
    -0.67
    ãĥĭ
    -0.65
    ®
    -0.64
    IRO
    -0.62
    ==
    -0.61
    umat
    -0.60
    NRS
    -0.59
    Hub
    -0.59
    Frame
    -0.58
    POSITIVE LOGITS
    Interstitial
    1.20
    -'
    0.86
     ',
    0.84
    taboola
    0.84
    .'
    0.82
    emouth
    0.80
    Cause
    0.80
    til
    0.78
     '.
    0.78
    tis
    0.76
    Activations Density 0.036%

    No Known Activations