© 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. 9-RES-JB
    11. 5067
    Prev
    Next
    INDEX
    Explanations

    instances where some form of continuation or growth is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating continuation or persistence of actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EStream
    -0.71
    starting
    -0.67
     Closing
    -0.67
     Dreams
    -0.63
    OTAL
    -0.62
     Correct
    -0.60
     endings
    -0.60
    ravis
    -0.60
     stopping
    -0.59
     Sure
    -0.58
    POSITIVE LOGITS
     accumulate
    1.14
     defy
    1.10
     dominate
    1.04
     deterior
    1.03
     refine
    0.99
     circulate
    0.98
     evolve
    0.98
     operate
    0.94
     occupy
    0.94
     thrive
    0.94
    Activations Density 0.036%

    No Known Activations