INDEX

Explanations

examples of different categories or items within a larger group

oai_token-act-pair · gpt-3.5-turbo

the word "even."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

rend

-0.94

HCR

-0.70

FG

-0.70

obi

-0.69

cel

-0.68

onomous

-0.65

ected

-0.64

ASE

-0.64

ãĤ¿

-0.64

rupt

-0.61

POSITIVE LOGITS

 remotely

0.92

 though

0.84

tho

0.70

ivari

0.70

 indirectly

0.68

romeda

0.66

 consider

0.64

handed

0.64

handedly

0.63

 moderately

0.63

Activations Density 0.073%

examples of different categories or items within a larger group

the word "even."

No Comments

No Known Activations