Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 13308
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of "impression", particularly focusing on expressing opinions or beliefs about something or someone

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of 'impression'

    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
    atts
    -0.76
    annis
    -0.72
    vez
    -0.70
    cross
    -0.68
    foreseen
    -0.66
    fighting
    -0.65
    undreds
    -0.62
    regulated
    -0.60
    cgi
    -0.60
    church
    -0.60
    POSITIVE LOGITS
     impression
    1.04
     impressions
    0.99
    eful
    0.89
    eless
    0.87
    uren
    0.84
    izable
    0.80
    istic
    0.79
    able
    0.77
    ably
    0.75
    terness
    0.72
    Activations Density 0.041%

    No Known Activations