INDEX

Explanations

summaries or summaries-related terms

oai_token-act-pair · gpt-3.5-turbo

terms related to summaries and the concept of summarization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 cosmetic

-0.63

pox

-0.63

 pity

-0.62

 colonial

-0.62

#$

-0.62

Atl

-0.60

Eye

-0.60

 itch

-0.59

 colonialism

-0.59

 implanted

-0.59

POSITIVE LOGITS

inez

1.11

 summ

1.01

umbn

0.92

ework

0.92

itely

0.87

onym

0.85

itions

0.84

ition

0.84

icals

0.83

onymous

0.83

Activations Density 0.019%

summaries or summaries-related terms

terms related to summaries and the concept of summarization

No Comments

No Known Activations