INDEX

Explanations

instances where the word "which" is mentioned

oai_token-act-pair · gpt-3.5-turbo

clauses starting with "which"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

Behind

-0.66

athi

-0.61

 Tome

-0.54

pad

-0.54

belt

-0.54

Gy

-0.51

ben

-0.51

bug

-0.51

Bas

-0.50

POSITIVE LOGITS

soever

0.83

xual

0.69

chwitz

0.66

psons

0.64

iannopoulos

0.62

NetMessage

0.61

abama

0.60

 contrasts

0.60

nces

0.59

venants

0.58

Activations Density 0.063%

instances where the word "which" is mentioned

clauses starting with "which"

No Comments

No Known Activations