INDEX

Explanations

sentences that critique societal norms and behaviors, particularly regarding humor and double standards in media

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.ï¿½

-0.77

----------

-0.76

.''

-0.72

,''

-0.72

Copyright

-0.70

tion

-0.67

.}

-0.67

`.

-0.66

properties

-0.65

-0.64

POSITIVE LOGITS

 haunted

0.72

 inexpl

0.70

 cannibal

0.69

 coughing

0.69

 scor

0.68

 endlessly

0.68

 sleek

0.68

 humming

0.68

 glowing

0.68

ooz

0.67

Activations Density 0.433%

sentences that critique societal norms and behaviors, particularly regarding humor and double standards in media

No Comments

No Known Activations