INDEX

Explanations

instances where someone is expressing interest in something or someone

oai_token-act-pair · gpt-3.5-turbo

expressions of interest or curiosity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Fail

-0.63

 stacked

-0.63

 testament

-0.61

âĶĢ

-0.61

ework

-0.61

 botched

-0.57

existence

-0.57

enberg

-0.57

 unchecked

-0.57

hemy

-0.56

POSITIVE LOGITS

 therein

0.75

ãĥĦ

0.73

ately

0.72

ENC

0.71

encies

0.69

iltr

0.67

enza

0.67

iotics

0.64

 parties

0.63

inery

0.63

Activations Density 0.037%

instances where someone is expressing interest in something or someone

expressions of interest or curiosity

No Comments

No Known Activations