INDEX

Explanations

questions directed at the reader

oai_token-act-pair · gpt-3.5-turbo

questions that address the audience directly

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

Lago

-0.70

ges

-0.69

rawdownloadcloneembedreportprint

-0.68

ruciating

-0.67

ospital

-0.66

borgh

-0.65

"},

-0.64

arc

-0.63

apo

-0.62

IPS

-0.62

POSITIVE LOGITS

 guys

1.09

tub

0.99

 prefer

0.93

 intend

0.91

're

0.90

 wanna

0.85

 ever

0.85

 want

0.84

 guessed

0.83

 subscribed

0.82

Activations Density 0.038%

questions directed at the reader

questions that address the audience directly

No Comments

No Known Activations