INDEX

Explanations

proper nouns, specifically names of people

oai_token-act-pair · gpt-3.5-turbo

references to notable individuals, specifically filmmakers and politicians

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

 Tune

-0.74

 antioxid

-0.68

yang

-0.62

 Duck

-0.61

XD

-0.61

 Tayyip

-0.61

 Erdogan

-0.60

Pok

-0.60

eering

-0.60

 Takeru

-0.59

POSITIVE LOGITS

owship

1.29

ritch

0.92

ats

0.83

ows

0.83

nuts

0.80

Winged

0.77

atan

0.77

ecided

0.76

umbs

0.76

angel

0.74

Activations Density 0.032%

proper nouns, specifically names of people

references to notable individuals, specifically filmmakers and politicians

No Comments

No Known Activations