© 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. 15414
    Prev
    Next
    INDEX
    Explanations

    references to installing or using software packages

    oai_token-act-pair · gpt-3.5-turbo

    mentions of institutions, specifically those related to technology and the internet

    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
     Tone
    -0.90
    theless
    -0.77
    berries
    -0.75
    DEN
    -0.71
    dress
    -0.66
     mustard
    -0.66
     QC
    -0.66
    ball
    -0.64
    OPLE
    -0.64
     KING
    -0.62
    POSITIVE LOGITS
    itutional
    1.44
    itution
    1.31
    inct
    1.29
    itute
    1.24
    alled
    1.15
    ances
    1.03
    ellation
    1.03
    alling
    1.02
    itutes
    1.01
    agram
    1.01
    Activations Density 0.011%

    No Known Activations