INDEX

Explanations

functions and programming syntax related terms

oai_token-act-pair · gpt-3.5-turbo

programming-related terms, specifically involving functions and error handling in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

".[

-0.77

kefeller

-0.75

 Gutenberg

-0.70

."[

-0.69

MSN

-0.65

APH

-0.64

Sov

-0.64

tumblr

-0.63

escent

-0.63

POSITIVE LOGITS

){

1.15

 args

0.94

):

0.88

 params

0.85

):

0.84

Args

0.81

args

0.75

={

0.73

params

0.69

env

0.67

Activations Density 0.072%

functions and programming syntax related terms

programming-related terms, specifically involving functions and error handling in code

No Comments

No Known Activations