INDEX

Explanations

technical terms related to data processing and analysis

oai_token-act-pair · gpt-3.5-turbo

technical terminology related to scientific and medical processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 hesitated

-0.66

 dodged

-0.65

 enthusi

-0.61

iami

-0.58

WARN

-0.58

jew

-0.58

kell

-0.57

 apologized

-0.56

 kissed

-0.56

 greeted

-0.56

POSITIVE LOGITS

 counterparts

0.95

 counterpart

0.80

 elsewhere

0.74

 realities

0.72

 ones

0.71

 existing

0.70

existing

0.70

alogue

0.62

 objectives

0.61

 backdrop

0.61

Activations Density 0.702%

technical terms related to data processing and analysis

technical terminology related to scientific and medical processes

No Comments

No Known Activations