INDEX

Explanations

statements or references indicating that there is nothing significant or noteworthy occurring

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Nothing" 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 @ 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

circ

-0.68

ste

-0.65

asio

-0.65

 highest

-0.64

lev

-0.62

ammad

-0.62

aic

-0.61

irgin

-0.61

amed

-0.61

CVE

-0.60

POSITIVE LOGITS

Else

1.14

 else

1.04

ĪĴ

0.96

 Else

0.94

ĸļ

0.88

Nothing

0.88

soever

0.85

nesses

0.83

theless

0.83

 Nothing

0.81

Activations Density 0.007%

statements or references indicating that there is nothing significant or noteworthy occurring

instances of the word "Nothing" in various contexts

No Comments

No Known Activations