INDEX

Explanations

proper nouns related to individuals

oai_token-act-pair · gpt-3.5-turbo

the repetition of the name "Henrik" 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 @ 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

terday

-0.76

EED

-0.73

 conclud

-0.72

eele

-0.69

anwhile

-0.65

ENTS

-0.65

Sax

-0.64

ENCY

-0.62

Reference

-0.62

ateral

-0.61

POSITIVE LOGITS

rique

1.26

ning

1.03

lein

0.98

riks

0.95

sel

0.95

rik

0.93

agar

0.92

kel

0.90

ricks

0.90

emy

0.90

Activations Density 0.017%

proper nouns related to individuals

the repetition of the name "Henrik" in various contexts

No Comments

No Known Activations