INDEX

Explanations

phrases related to actions or activities

oai_token-act-pair · gpt-3.5-turbo

instances of the word "out" 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pim

-0.76

 ankles

-0.74

 multim

-0.69

 wallets

-0.68

 averaging

-0.64

 wrists

-0.64

 heels

-0.64

 lottery

-0.63

 reckoning

-0.63

 ears

-0.61

POSITIVE LOGITS

rey

1.02

inho

0.96

atis

0.88

ube

0.86

lov

0.86

hest

0.84

reau

0.83

cade

0.80

hee

0.80

ek

0.78

Activations Density 0.071%

phrases related to actions or activities

instances of the word "out" in various contexts

No Comments

No Known Activations