INDEX

Explanations

phrases related to prevention or hindrance

oai_token-act-pair · gpt-3.5-turbo

instances of the word "from" indicating prevention or obstruction

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

atl

-0.80

bush

-0.79

oy

-0.76

hello

-0.76

uid

-0.73

tops

-0.72

aic

-0.72

quickShipAvailable

-0.71

oct

-0.69

cule

-0.69

POSITIVE LOGITS

 accessing

0.88

 completing

0.80

 afar

0.79

 anywhere

0.77

 obtaining

0.77

 scrimmage

0.77

 achieving

0.77

 participating

0.76

 reaching

0.75

 either

0.74

Activations Density 0.046%

phrases related to prevention or hindrance

instances of the word "from" indicating prevention or obstruction

No Comments

No Known Activations