© 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. 6-RES-JB
    11. 18445
    Prev
    Next
    INDEX
    Explanations

    instances where something is being stored or kept in a specific location or container

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of storage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ="#
    -0.80
    etti
    -0.76
    sey
    -0.74
    omen
    -0.74
    hire
    -0.73
    icer
    -0.72
     Rider
    -0.69
    caster
    -0.66
    ello
    -0.65
    zai
    -0.65
    POSITIVE LOGITS
     reserve
    0.90
     secret
    0.85
     freezer
    0.84
     biod
    0.81
     limbo
    0.80
     secrecy
    0.80
     reserves
    0.80
    ngth
    0.77
     refriger
    0.76
     indefinitely
    0.76
    Activations Density 0.286%

    No Known Activations