INDEX

Explanations

instances of 'Q&A' or question and answer sessions

oai_token-act-pair · gpt-3.5-turbo

references to question and answer sessions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

intent

-0.80

wikipedia

-0.73

fell

-0.71

sea

-0.70

bats

-0.69

acements

-0.69

origin

-0.68

EStreamFrame

-0.68

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.67

sei

-0.67

POSITIVE LOGITS

 session

1.27

 sessions

1.19

 Session

0.94

 interview

0.80

 conversation

0.78

 guru

0.78

 moder

0.78

cation

0.77

 Answers

0.77

 panel

0.76

Activations Density 0.073%

instances of 'Q&A' or question and answer sessions

references to question and answer sessions

No Comments

No Known Activations