INDEX

Explanations

phrases related to conflicts or disputes

oai_token-act-pair · gpt-3.5-turbo

expressions related to conflicts or debates

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

VPN

-0.74

kie

-0.73

ocks

-0.72

kson

-0.70

phia

-0.70

igmatic

-0.69

cks

-0.66

quist

-0.66

ROR

-0.66

unker

-0.65

POSITIVE LOGITS

 Olympia

0.61

LW

0.60

Mer

0.60

 Camel

0.59

 Lois

0.58

 moot

0.58

 Herman

0.57

RTX

0.57

 Vision

0.57

 Armageddon

0.56

Activations Density 0.351%

phrases related to conflicts or disputes

expressions related to conflicts or debates

No Comments

No Known Activations