INDEX

Explanations

adjectives describing purity

oai_token-act-pair · gpt-3.5-turbo

references to concepts and qualities associated with purity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

apter

-0.82

 closest

-0.70

 prominently

-0.70

otos

-0.65

ieri

-0.64

agements

-0.60

 Peninsula

-0.59

Mub

-0.59

 closely

-0.58

ails

-0.58

POSITIVE LOGITS

bred

1.29

st

0.97

waters

0.93

blood

0.89

0.86

blooded

0.86

 bliss

0.82

 enjoyment

0.80

 adrenaline

0.79

 evil

0.77

Activations Density 0.022%

adjectives describing purity

references to concepts and qualities associated with purity

No Comments

No Known Activations