INDEX

Explanations

technical terms and specific phrases related to data and processes

oai_token-act-pair · gpt-3.5-turbo

terms related to issues or problems 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 @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

lance

-0.71

luaj

-0.69

DragonMagazine

-0.69

raltar

-0.67

dated

-0.65

ionage

-0.65

terday

-0.65

zie

-0.63

BLIC

-0.63

zed

-0.62

POSITIVE LOGITS

 itself

1.38

 recipient

1.00

 owner

0.98

 sender

0.90

 nearest

0.88

 issuer

0.86

 themselves

0.84

 oneself

0.83

owner

0.82

 creator

0.82

Activations Density 0.465%

technical terms and specific phrases related to data and processes

terms related to issues or problems in various contexts

No Comments

No Known Activations