INDEX

Explanations

the word "indent" and related variations

oai_token-act-pair · gpt-3.5-turbo

mentions of specific names and technical terms related to indentations and annotations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ELY

-0.78

IRD

-0.76

roc

-0.74

 Canaveral

-0.72

ASED

-0.72

ById

-0.71

ross

-0.70

estone

-0.69

ISM

-0.68

istic

-0.67

POSITIVE LOGITS

xual

1.04

ingen

0.88

*/(

0.79

 lapse

0.79

 markup

0.79

raints

0.78

ificant

0.77

psey

0.77

eanor

0.74

uckland

0.70

Activations Density 0.032%

the word "indent" and related variations

mentions of specific names and technical terms related to indentations and annotations

No Comments

No Known Activations