INDEX

Explanations

sentences containing warnings or advice

oai_token-act-pair · gpt-3.5-turbo

instances of the word "warned."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

animate

-0.74

Interstitial

-0.71

dx

-0.68

EMS

-0.67

NAS

-0.66

á

-0.65

frey

-0.65

anuts

-0.65

PB

-0.64

Boot

-0.64

POSITIVE LOGITS

warn

1.03

 Warn

0.96

warning

0.93

 omin

0.88

 warnings

0.88

 warns

0.87

 warn

0.83

 warning

0.82

 warned

0.81

ariat

0.74

Activations Density 0.018%

sentences containing warnings or advice

instances of the word "warned."

No Comments

No Known Activations