INDEX

Explanations

mentions of specific locations or events, particularly related to media or news coverage

oai_token-act-pair · gpt-3.5-turbo

named entities related to places, organizations, and events

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

PDATE

-0.65

 USDA

-0.62

 causation

-0.61

amples

-0.61

ELY

-0.60

ãĤ£

-0.60

amsung

-0.59

agy

-0.59

Ö¼

-0.58

worldly

-0.58

POSITIVE LOGITS

 Festival

0.77

 Consortium

0.77

Council

0.77

 Centre

0.76

stice

0.74

 Exchange

0.73

ptroller

0.72

 Toll

0.72

ressor

0.71

abulary

0.70

Activations Density 0.211%

mentions of specific locations or events, particularly related to media or news coverage

named entities related to places, organizations, and events

No Comments

No Known Activations