INDEX

Explanations

words related to conflict or confrontation

oai_token-act-pair · gpt-3.5-turbo

words related to various forms of expression and artistic disciplines

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

gaard

-0.75

 Gret

-0.68

 grit

-0.67

 Cheong

-0.66

Adds

-0.63

NK

-0.62

places

-0.62

 independents

-0.61

zag

-0.58

 Gron

-0.58

POSITIVE LOGITS

ioxide

0.80

eta

0.80

ophen

0.79

gypt

0.76

pillar

0.76

OSS

0.76

nect

0.73

ÃĽ

0.72

Corp

0.71

emn

0.71

Activations Density 0.092%

words related to conflict or confrontation

words related to various forms of expression and artistic disciplines

No Comments

No Known Activations