INDEX

Explanations

adjectives expressing disapproval or criticism

oai_token-act-pair · gpt-3.5-turbo

negative judgments or criticisms regarding actions, policies, and ideas

oai_token-act-pair · gpt-4o-mini Triggered 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

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

quart

-0.77

interrupted

-0.68

semble

-0.66

tains

-0.65

essor

-0.63

 ravaged

-0.63

 dominate

-0.60

odan

-0.60

essed

-0.59

 peaks

-0.59

POSITIVE LOGITS

 because

0.83

 unless

0.74

 underestimate

0.73

 insofar

0.71

 enough

0.69

 underest

0.66

ãħĭãħĭ

0.66

necess

0.66

ãĤ¹ãĥĪ

0.66

 detract

0.64

Activations Density 0.223%

adjectives expressing disapproval or criticism

negative judgments or criticisms regarding actions, policies, and ideas

No Comments

No Known Activations