INDEX

Explanations

words or phrases related to cause-and-effect scenarios or consequences

oai_token-act-pair · gpt-3.5-turbo

phrases concerning the potential consequences or outcomes of various actions or events

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

ament

-0.85

mens

-0.84

cius

-0.77

staff

-0.75

ways

-0.75

aments

-0.72

bors

-0.71

pole

-0.70

tesy

-0.69

stra

-0.68

POSITIVE LOGITS

 unfold

0.84

 unfolding

0.80

 transpired

0.79

uate

0.78

 Ambro

0.78

 happen

0.74

uates

0.73

uating

0.71

 Happ

0.70

 next

0.68

Activations Density 0.039%

words or phrases related to cause-and-effect scenarios or consequences

phrases concerning the potential consequences or outcomes of various actions or events

No Comments

No Known Activations