INDEX

Explanations

programming code related to defining functions and roles

oai_token-act-pair · gpt-3.5-turbo

definitions and declarations in programming code

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

-0.96

bank

-0.82

ander

-0.80

worthiness

-0.80

polit

-0.72

Ã£

-0.71

emb

-0.70

won

-0.69

 comprom

-0.69

isdom

-0.69

POSITIVE LOGITS

 Clar

0.69

¶ħ

0.69

__

0.68

fn

0.68

 loop

0.67

 Create

0.66

 Decl

0.65

 Âł Âł Âł Âł

0.65

 attm

0.64

 Purpose

0.63

Activations Density 0.024%

programming code related to defining functions and roles

definitions and declarations in programming code

No Comments

No Known Activations