INDEX

Explanations

references to future plans or strategies

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "plans" 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 @ 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

 ILCS

-0.87

Cause

-0.74

 Stain

-0.72

 Temper

-0.71

Interstitial

-0.70

mint

-0.69

INTON

-0.69

aud

-0.63

inas

-0.61

Naz

-0.61

POSITIVE LOGITS

etary

0.85

 Parenthood

0.83

escape

0.82

isphere

0.81

emaker

0.78

creen

0.78

obs

0.78

 ahead

0.77

etting

0.77

ets

0.77

Activations Density 0.040%

references to future plans or strategies

occurrences of the word "plans" in various contexts

No Comments

No Known Activations