INDEX

Explanations

references to the legality or illegality of various activities or substances

oai_token-act-pair · gpt-3.5-turbo

terms related to the legality of marijuana

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

ortment

-0.71

PsyNetMessage

-0.65

ortun

-0.63

Reb

-0.62

aida

-0.62

ravings

-0.61

aleb

-0.61

ILA

-0.61

quart

-0.60

 Advent

-0.60

POSITIVE LOGITS

 enough

0.97

isable

0.86

izable

0.85

aneously

0.81

 anyway

0.79

 unless

0.78

 anymore

0.77

.''

0.73

 ashore

0.72

 Ichigo

0.72

Activations Density 0.295%

references to the legality or illegality of various activities or substances

terms related to the legality of marijuana

No Comments

No Known Activations