INDEX

Explanations

programming-related terms and concepts related to defining and declaring

oai_token-act-pair · gpt-3.5-turbo

terms related to defining and declaring variables or constants in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

bill

-0.87

fare

-0.84

bite

-0.77

Crunch

-0.75

osate

-0.75

waters

-0.74

shaw

-0.73

 Recession

-0.73

bourne

-0.72

POSITIVE LOGITS

 bindings

0.97

 deprecated

0.86

 syntax

0.85

 defaults

0.82

 dependencies

0.81

 extensions

0.81

 CLIENT

0.80

initions

0.78

$_

0.77

 statically

0.76

Activations Density 0.065%

programming-related terms and concepts related to defining and declaring

terms related to defining and declaring variables or constants in programming

No Comments

No Known Activations