© 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. 8-RES-JB
    11. 4581
    Prev
    Next
    INDEX
    Explanations

    years and time periods

    oai_token-act-pair · gpt-3.5-turbo

    the presence of commas and conjunctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olo
    -0.75
    izen
    -0.74
    iously
    -0.74
    enary
    -0.71
    ries
    -0.68
    ivated
    -0.67
    eworthy
    -0.66
    obos
    -0.66
    uce
    -0.65
    iev
    -0.65
    POSITIVE LOGITS
     albeit
    0.96
     meaning
    0.96
     huh
    0.94
     whereas
    0.90
     hence
    0.86
     but
    0.83
     although
    0.79
     eh
    0.72
     insofar
    0.70
     therefore
    0.70
    Activations Density 0.441%

    No Known Activations