© 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. 226
    Prev
    Next
    INDEX
    Explanations

    phrases related to being behind or following others

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to trailing and being behind in context

    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
    ylum
    -0.86
    ity
    -0.71
    osate
    -0.71
    ALLY
    -0.70
    ifications
    -0.69
    entric
    -0.66
    iation
    -0.66
    ulus
    -0.66
    ocker
    -0.65
    pton
    -0.65
    POSITIVE LOGITS
    bare
    0.86
    rils
    0.83
    beat
    0.82
    endas
    0.74
    doors
    0.73
    GGGG
    0.73
    ttes
    0.73
    dro
    0.71
    ĸļ
    0.68
     tongues
    0.67
    Activations Density 0.009%

    No Known Activations