INDEX

Explanations

hidden items or elements within a context

oai_token-act-pair · gpt-3.5-turbo

the concept of "hidden" aspects or elements within various contexts

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

nia

-0.72

rehens

-0.72

asus

-0.71

umbn

-0.71

Pwr

-0.69

igel

-0.68

alon

-0.68

rontal

-0.67

adjusted

-0.66

create

-0.66

POSITIVE LOGITS

 gems

0.97

gem

0.91

 depths

0.88

 stash

0.86

 hidden

0.83

 behind

0.83

 treasures

0.82

 recess

0.81

 treasure

0.80

 beneath

0.79

Activations Density 0.029%

hidden items or elements within a context

the concept of "hidden" aspects or elements within various contexts

No Comments

No Known Activations