INDEX

Explanations

mentions of different wars or war-related terms

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "wars"

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

ATURE

-0.65

AUT

-0.63

STER

-0.63

SOURCE

-0.63

YL

-0.60

gow

-0.60

Dialogue

-0.58

 Accuracy

-0.57

Asset

-0.57

nosis

-0.57

POSITIVE LOGITS

hip

1.33

hips

1.30

pace

1.08

poons

0.95

uits

0.94

hops

0.94

pread

0.94

cale

0.92

mith

0.87

pite

0.85

Activations Density 0.029%

mentions of different wars or war-related terms

occurrences of the word "wars"

No Comments

No Known Activations