INDEX

Explanations

adjectives and verbs related to expressing opinions or attitudes

oai_token-act-pair · gpt-3.5-turbo

terms related to strictness and transparency in decision-making

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ioxide

-0.74

brance

-0.68

aleb

-0.66

anyon

-0.65

 vanishing

-0.64

ruction

-0.64

 McDonnell

-0.63

Ranked

-0.61

tein

-0.61

ogg

-0.60

POSITIVE LOGITS

 enough

0.81

ãĥ¼ãĤ¯

0.76

enough

0.74

ceptive

0.72

 reacting

0.71

looking

0.71

ergic

0.70

 minded

0.70

atively

0.70

 towards

0.68

Activations Density 0.205%

adjectives and verbs related to expressing opinions or attitudes

terms related to strictness and transparency in decision-making

No Comments

No Known Activations