INDEX

Explanations

warnings or alerts expressed in various contexts

oai_token-act-pair · gpt-3.5-turbo

instances of the word "warned" 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 @ 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

Interstitial

-0.73

anuts

-0.66

animate

-0.66

 ILCS

-0.66

á

-0.64

dx

-0.63

portion

-0.61

NAS

-0.61

rafted

-0.60

adesh

-0.59

POSITIVE LOGITS

warn

1.04

warning

0.95

 Warn

0.89

 omin

0.86

 warnings

0.82

ingly

0.81

 warns

0.80

 caution

0.78

 warn

0.77

 warning

0.74

Activations Density 0.018%

warnings or alerts expressed in various contexts

instances of the word "warned" and its variations

No Comments

No Known Activations