INDEX

Explanations

words related to being based on something

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate something is grounded or founded on specific information or assumptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

nel

-0.75

shr

-0.72

asar

-0.71

ESE

-0.69

osen

-0.68

antha

-0.68

apes

-0.68

icz

-0.67

dra

-0.66

å¥³

-0.65

POSITIVE LOGITS

 loosely

0.88

 upon

0.81

awaru

0.71

 solely

0.70

ragon

0.67

 certific

0.66

tesy

0.64

edience

0.63

 transcription

0.63

 paycheck

0.63

Activations Density 0.037%

words related to being based on something

phrases that indicate something is grounded or founded on specific information or assumptions

No Comments

No Known Activations