INDEX

Explanations

warnings or cautionary statements

oai_token-act-pair · gpt-3.5-turbo

instances of the word "warn" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 ILCS

-0.82

Interstitial

-0.77

mite

-0.74

anuts

-0.72

OVA

-0.71

dx

-0.71

cube

-0.70

vez

-0.68

Answer

-0.67

irrel

-0.66

POSITIVE LOGITS

 against

1.09

 omin

0.96

 listeners

0.87

 caution

0.82

warn

0.82

ingly

0.76

 viewers

0.75

 warned

0.75

 readers

0.75

 beforehand

0.75

Activations Density 0.042%

warnings or cautionary statements

instances of the word "warn" and its variations

No Comments

No Known Activations