INDEX

Explanations

phrases or words related to finding common ground or shared agreements

oai_token-act-pair · gpt-3.5-turbo

references to common ground or consensus in discussions

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

 notor

-0.71

atto

-0.69

 tatt

-0.68

bil

-0.66

glomer

-0.63

uked

-0.61

 bailed

-0.60

 accomp

-0.60

hid

-0.60

pload

-0.59

POSITIVE LOGITS

 footing

0.76

places

0.76

cover

0.73

notes

0.71

aminer

0.69

¢

0.66

Ground

0.66

enture

0.65

planes

0.65

itement

0.64

Activations Density 0.014%

phrases or words related to finding common ground or shared agreements

references to common ground or consensus in discussions

No Comments

No Known Activations