INDEX

Explanations

references to specific versions or variations of a product or software release

oai_token-act-pair · gpt-3.5-turbo

numeric references to versions or releases of software or products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

awaru

-0.85

rolet

-0.71

icularly

-0.67

ilant

-0.65

arov

-0.64

ilitating

-0.64

efully

-0.63

ordinate

-0.62

orically

-0.61

depending

-0.61

POSITIVE LOGITS

XL

0.73

ÃĹ

0.73

Ħ¢

0.71

rd

0.71

DM

0.70

ouver

0.69

+,

0.68

nd

0.68

0.67

Activations Density 0.116%

references to specific versions or variations of a product or software release

numeric references to versions or releases of software or products

No Comments

No Known Activations