INDEX

Explanations

code snippets and programming-related terms

oai_token-act-pair · gpt-3.5-turbo

programming terminology and syntax elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

folios

-0.70

zbek

-0.67

Tube

-0.67

outhern

-0.67

âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦

-0.65

icularly

-0.63

hesive

-0.63

Ø§Ø

-0.63

iasis

-0.63

arnaev

-0.63

POSITIVE LOGITS

"{

0.94

 Math

0.93

str

0.91

 null

0.90

$_

0.89

 args

0.88

",

0.87

nil

0.87

 NULL

0.87

"%

0.85

Activations Density 0.058%

code snippets and programming-related terms

programming terminology and syntax elements

No Comments

No Known Activations