INDEX

Explanations

phrases or words related to reflecting, representation or mirroring

oai_token-act-pair · gpt-3.5-turbo

phrases related to reflection or consideration of circumstances and opinions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

icz

-0.77

ciating

-0.72

 externalToEVAOnly

-0.71

corn

-0.70

ccess

-0.65

queue

-0.64

ike

-0.63

feet

-0.61

anch

-0.61

é¾įå

-0.61

POSITIVE LOGITS

ively

0.99

 poorly

0.85

uate

0.85

 upon

0.82

 reflected

0.82

 sunlight

0.81

 negatively

0.81

iveness

0.80

 reflections

0.80

uates

0.79

Activations Density 0.048%

phrases or words related to reflecting, representation or mirroring

phrases related to reflection or consideration of circumstances and opinions

No Comments

No Known Activations