INDEX

Explanations

mentions of specific individuals or entities

oai_token-act-pair · gpt-3.5-turbo

determiners and descriptors related to people, roles, or entities 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 @ 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

rison

-0.76

isks

-0.68

midt

-0.68

chuk

-0.66

ourses

-0.66

nesday

-0.66

ants

-0.63

antle

-0.62

Cow

-0.62

arks

-0.61

POSITIVE LOGITS

pport

0.79

 antit

0.78

TBD

0.72

Rated

0.72

 prone

0.69

 habitable

0.69

 compatible

0.69

 dstg

0.69

pired

0.68

quartered

0.67

Activations Density 0.365%

mentions of specific individuals or entities

determiners and descriptors related to people, roles, or entities in various contexts

No Comments

No Known Activations