INDEX

Explanations

the phrase "Big" followed by a number, potentially related to entities or classifications

oai_token-act-pair · gpt-3.5-turbo

references to the term "Big" followed by numbers, indicative of significant entities or groups

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 confir

-0.91

idency

-0.83

anwhile

-0.78

veyard

-0.78

 livest

-0.77

Downloadha

-0.74

theless

-0.74

 Cheong

-0.73

 Emin

-0.73

PLIED

-0.71

POSITIVE LOGITS

gest

1.21

ger

1.04

glers

0.88

 Brother

0.79

Integer

0.76

big

0.75

amy

0.75

gie

0.74

Boss

0.74

rug

0.73

Activations Density 0.016%

the phrase "Big" followed by a number, potentially related to entities or classifications

references to the term "Big" followed by numbers, indicative of significant entities or groups

No Comments

No Known Activations