INDEX

Explanations

short phrases or sentences found on various items like stickers, shirts, banners, or signs

oai_token-act-pair · gpt-3.5-turbo

text related to signs, stickers, or slogans

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

aneers

-0.78

ynchronous

-0.77

 accelerate

-0.76

kus

-0.75

GET

-0.72

isky

-0.71

 listeners

-0.71

humans

-0.71

 nerv

-0.70

imester

-0.70

POSITIVE LOGITS

 inscription

1.25

 engraved

1.12

 etched

1.11

 markings

1.10

 inscribed

1.09

 swast

1.08

 plaque

1.03

 signage

1.00

prints

0.97

 banners

0.96

Activations Density 0.971%

short phrases or sentences found on various items like stickers, shirts, banners, or signs

text related to signs, stickers, or slogans

No Comments

No Known Activations