INDEX

Explanations

words starting with "ver" that are related to verification or truth

oai_token-act-pair · gpt-3.5-turbo

terms related to verification and validation

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

ENDED

-0.80

ered

-0.73

»Ĵ

-0.70

hyde

-0.69

emi

-0.68

NetMessage

-0.67

 Disorder

-0.66

ENS

-0.66

 Fever

-0.63

 flyers

-0.63

POSITIVE LOGITS

ifiable

1.11

itable

1.05

ulent

1.02

bat

0.92

ulence

0.91

dict

0.90

gue

0.89

itably

0.88

idian

0.86

bal

0.86

Activations Density 0.010%

words starting with "ver" that are related to verification or truth

terms related to verification and validation

No Comments

No Known Activations