INDEX

Explanations

references to scripts or scripting in a technical context

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "script" and its variations in a programming context

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

 Psychiat

-0.77

coat

-0.71

arthed

-0.68

kHz

-0.68

obby

-0.66

abouts

-0.66

Dew

-0.66

ŃĶ

-0.65

bring

-0.65

 Floor

-0.63

POSITIVE LOGITS

 scripting

0.98

 script

0.97

script

0.94

 scripts

0.94

ural

0.93

scripts

0.92

 interpreter

0.90

Pub

0.85

Deploy

0.84

urally

0.82

Activations Density 0.011%

references to scripts or scripting in a technical context

occurrences of the word "script" and its variations in a programming context

No Comments

No Known Activations