INDEX

Explanations

phrases related to challenges, conflicts, and opposition

oai_token-act-pair · gpt-3.5-turbo

references to the concept of struggle 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 @ 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

omin

-0.84

Male

-0.73

cise

-0.72

idel

-0.71

repl

-0.71

othy

-0.68

entric

-0.68

urate

-0.68

ramer

-0.67

ateur

-0.67

POSITIVE LOGITS

 Struggle

1.28

 struggle

0.94

 struggles

0.85

 Sioux

0.83

ĸļ

0.80

ggle

0.75

icago

0.73

 struggled

0.69

 against

0.69

ingly

0.68

Activations Density 0.012%

phrases related to challenges, conflicts, and opposition

references to the concept of struggle in various contexts

No Comments

No Known Activations