INDEX

Explanations

words related to physical health and medical conditions

oai_token-act-pair · gpt-3.5-turbo

terms related to health and wellness

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

$.

-0.64

yond

-0.57

!.

-0.55

é¾įå

-0.55

+.

-0.54

`.

-0.54

FactoryReloaded

-0.53

ĸļ

-0.52

=]

-0.51

 rather

-0.51

POSITIVE LOGITS

 consists

0.61

iest

0.58

hest

0.55

 dilemma

0.55

 consisted

0.54

 maintains

0.54

 comprises

0.52

 extends

0.52

 refers

0.51

argument

0.51

Activations Density 1.241%

words related to physical health and medical conditions

terms related to health and wellness

No Comments

No Known Activations