INDEX

Explanations

transcripts of conversations or events

oai_token-act-pair · gpt-3.5-turbo

references to transcripts of spoken content or documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Magikarp

-0.76

ndra

-0.73

jri

-0.62

GPU

-0.62

GBT

-0.62

 maternity

-0.61

rimp

-0.60

bledon

-0.59

yu

-0.59

AGES

-0.58

POSITIVE LOGITS

 transcript

0.95

ural

0.94

ions

0.92

 transcription

0.92

 excerpt

0.90

ographer

0.87

ophone

0.87

 Transcript

0.86

 taped

0.85

 excerpts

0.81

Activations Density 0.038%

transcripts of conversations or events

references to transcripts of spoken content or documents

No Comments

No Known Activations