INDEX

Explanations

questions being answered

oai_token-act-pair · gpt-3.5-turbo

phrases that involve addressing questions or inquiries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

paces

-0.69

issance

-0.68

 achieves

-0.65

obiles

-0.62

flix

-0.62

iture

-0.61

 assets

-0.61

;;;;;;;;;;;;

-0.60

acent

-0.59

artifacts

-0.58

POSITIVE LOGITS

 question

1.97

 questions

1.96

 QUEST

1.62

 Questions

1.54

question

1.54

 Question

1.53

 queries

1.43

Question

1.41

quest

1.34

Questions

1.32

Activations Density 0.226%

questions being answered

phrases that involve addressing questions or inquiries

No Comments

No Known Activations