INDEX

Explanations

phrases describing specific scenarios or cases

oai_token-act-pair · gpt-3.5-turbo

instances of the word "case" in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

uld

-0.77

itionally

-0.76

urses

-0.73

uilt

-0.73

kefeller

-0.72

olor

-0.72

urd

-0.71

icc

-0.70

urdy

-0.70

rush

-0.68

POSITIVE LOGITS

mma

0.86

pheus

0.68

çĭ

0.66

abouts

0.65

>>>>>>>>

0.65

achy

0.64

 scenario

0.62

 surviv

0.62

cases

0.61

 AUTH

0.61

Activations Density 0.027%

phrases describing specific scenarios or cases

instances of the word "case" in various contexts

No Comments

No Known Activations