INDEX

Explanations

sentences related to logical reasoning and personal improvement

oai_token-act-pair · gpt-3.5-turbo

logical reasoning and decision-making processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Sloan

-0.57

orsi

-0.55

Ã¨re

-0.55

 referring

-0.55

 Finance

-0.53

-0.52

 Ãī

-0.51

 Scand

-0.49

 thanking

-0.49

 Bearing

-0.49

POSITIVE LOGITS

iped

0.66

endas

0.61

ictionary

0.59

thood

0.57

ilan

0.56

aughs

0.55

hetics

0.55

isphere

0.54

aband

0.54

redients

0.54

Activations Density 1.352%

sentences related to logical reasoning and personal improvement

logical reasoning and decision-making processes

No Comments

No Known Activations