INDEX

Explanations

phrases related to taking actions or accepting responsibilities

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate taking on roles or responsibilities

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Anim

-0.75

WA

-0.70

Prev

-0.69

States

-0.68

anim

-0.65

Pic

-0.65

Compar

-0.65

ONSORED

-0.65

WARE

-0.64

Loading

-0.62

POSITIVE LOGITS

erous

1.01

 tremend

0.75

 Flavoring

0.73

 board

0.73

unal

0.71

 roles

0.69

*/(

0.69

emonic

0.69

 immortality

0.68

Downloadha

0.67

Activations Density 0.026%

phrases related to taking actions or accepting responsibilities

phrases that indicate taking on roles or responsibilities

No Comments

No Known Activations