INDEX

Explanations

numeric or alphanumeric sequences

oai_token-act-pair · gpt-3.5-turbo

numeric values related to scores or rankings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 gren

-0.65

CRA

-0.62

vertis

-0.59

taboola

-0.59

 Colt

-0.58

staff

-0.58

 rushed

-0.57

 deadlines

-0.57

miah

-0.57

retch

-0.55

POSITIVE LOGITS

entric

0.79

+,

0.77

+.

0.77

sum

0.71

0.70

DX

0.68

Edit

0.67

âĢ³

0.66

OGR

0.65

 Tactics

0.65

Activations Density 0.068%

numeric or alphanumeric sequences

numeric values related to scores or rankings

No Comments

No Known Activations