INDEX

Explanations

phrases related to hidden or secret things

oai_token-act-pair · gpt-3.5-turbo

instances of the word "hidden" 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 @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

Pwr

-0.80

nia

-0.76

Ħ¢

-0.76

rehens

-0.75

ctive

-0.74

urses

-0.74

alon

-0.73

annis

-0.71

acket

-0.70

ucc

-0.69

POSITIVE LOGITS

gem

1.01

 gems

0.92

 recess

0.89

 hidden

0.87

 behind

0.84

 stash

0.79

 treasures

0.78

eas

0.77

 hatch

0.77

 Hidden

0.77

Activations Density 0.027%

phrases related to hidden or secret things

instances of the word "hidden" in various contexts

No Comments

No Known Activations