INDEX

Explanations

keywords related to attributes or qualities

oai_token-act-pair · gpt-3.5-turbo

references to various attributes and their significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

fare

-0.85

analysis

-0.71

tic

-0.70

cow

-0.69

isky

-0.68

corn

-0.68

 TRAN

-0.67

tical

-0.66

NAS

-0.66

gone

-0.66

POSITIVE LOGITS

 attributes

0.97

 attribute

0.90

iveness

0.85

ively

0.83

mentation

0.82

wcsstore

0.77

ifer

0.77

attribute

0.77

 descript

0.77

reys

0.76

Activations Density 0.005%

keywords related to attributes or qualities

references to various attributes and their significance

No Comments

No Known Activations