INDEX

Explanations

phrases related to processes or actions

oai_token-act-pair · gpt-3.5-turbo

phrases that refer to ongoing actions or processes

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

 Flavoring

-0.65

 cents

-0.59

rib

-0.58

irie

-0.56

zan

-0.56

resent

-0.55

 Torn

-0.55

 eyebrows

-0.54

 millennium

-0.54

 anchor

-0.54

POSITIVE LOGITS

éŃĶ

0.85

æĦ

0.85

 process

0.82

ions

0.81

Shape

0.80

aday

0.78

ional

0.77

IONS

0.74

ä»£

0.74

ivity

0.73

Activations Density 0.023%

phrases related to processes or actions

phrases that refer to ongoing actions or processes

No Comments

No Known Activations