INDEX

Explanations

programming language keywords and related terms

oai_token-act-pair · gpt-3.5-turbo

terms related to computer programming and compilation processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

neck

-0.83

fm

-0.77

gren

-0.73

hillary

-0.73

mi

-0.72

mid

-0.71

nexus

-0.71

lyak

-0.70

 unsett

-0.70

bane

-0.70

POSITIVE LOGITS

Services

0.98

âĶĢâĶĢâĶĢâĶĢ

0.80

Rules

0.76

urally

0.73

|--

0.72

Org

0.71

 Errors

0.70

 Guidelines

0.69

Tool

0.69

BILITY

0.69

Activations Density 0.123%

programming language keywords and related terms

terms related to computer programming and compilation processes

No Comments

No Known Activations