INDEX

Explanations

the word or part of the word 'legend'

oai_token-act-pair · gpt-3.5-turbo

terms related to legality or legal concepts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

âķĲâķĲ

-0.69

ter

-0.65

ting

-0.64

terday

-0.64

 Bake

-0.63

KER

-0.61

 choking

-0.58

 Divinity

-0.58

 waiting

-0.57

ters

-0.57

POSITIVE LOGITS

itimate

1.27

isl

1.13

acies

1.06

acy

1.06

enic

1.05

rett

0.99

uin

0.97

lav

0.94

ends

0.93

roups

0.92

Activations Density 0.030%

the word or part of the word 'legend'

terms related to legality or legal concepts

No Comments

No Known Activations