INDEX

Explanations

references to lips and lip-related products or attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.8.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

 Leap

-0.79

ENCY

-0.77

ISION

-0.75

IRD

-0.73

 Rhino

-0.71

NESS

-0.69

WER

-0.67

ADRA

-0.67

Zed

-0.67

Ùİ

-0.65

POSITIVE LOGITS

sticks

1.03

ids

1.02

etsk

0.98

stick

0.93

atures

0.93

seys

0.92

ograph

0.91

 gloss

0.91

artisan

0.87

ĺħ

0.87

Activations Density 0.022%

references to lips and lip-related products or attributes

No Comments

No Known Activations