© 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. 7-RES-JB
    11. 23376
    Prev
    Next
    INDEX
    Explanations

    phrases related to consequences or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    references to the consequences or outcomes of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gged
    -0.86
    uni
    -0.80
    jab
    -0.76
    ovi
    -0.74
    ajo
    -0.71
    licks
    -0.66
    yu
    -0.65
    yi
    -0.64
    tailed
    -0.62
    chens
    -0.62
    POSITIVE LOGITS
     fallout
    0.96
     aftermath
    0.87
    noon
    0.76
     thereof
    0.76
    TPPStreamerBot
    0.73
     transpired
    0.71
    aneously
    0.69
    eatures
    0.69
     Effects
    0.68
     cleanup
    0.66
    Activations Density 0.047%

    No Known Activations