INDEX

Explanations

phrases related to negative connotations, criticism, and conflict

oai_token-act-pair · gpt-3.5-turbo

terms related to dishonesty and deception

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

©¶æ

-0.72

sonian

-0.71

 ILCS

-0.61

 unification

-0.61

 fert

-0.61

Aad

-0.61

Lub

-0.59

 runoff

-0.58

 custod

-0.58

RGB

-0.57

POSITIVE LOGITS

oked

1.46

oking

1.25

oke

0.86

ependent

0.80

okers

0.80

imentary

0.77

mares

0.76

ombat

0.75

okes

0.75

aukee

0.73

Activations Density 0.009%

phrases related to negative connotations, criticism, and conflict

terms related to dishonesty and deception

No Comments

No Known Activations