INDEX

Explanations

programming code snippets containing specific keywords and structures

oai_token-act-pair · gpt-3.5-turbo

programming-related terms and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

conservancy

-0.76

ktop

-0.71

 afore

-0.69

ãĢı

-0.67

 facult

-0.60

 lightning

-0.60

theless

-0.59

 Helsinki

-0.59

 anthrop

-0.58

 CARE

-0.57

POSITIVE LOGITS

1.20

Prev

0.93

Args

0.93

={

0.84

Num

0.83

=(

0.80

=[

0.80

Val

0.79

name

0.79

args

0.78

Activations Density 0.092%

programming code snippets containing specific keywords and structures

programming-related terms and structures

No Comments

No Known Activations