INDEX

Explanations

phrases indicating a high degree or extent of something

oai_token-act-pair · gpt-3.5-turbo

expressions of generality or vagueness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ortmund

-0.72

-0.68

TEXTURE

-0.67

DEBUG

-0.67

AMY

-0.66

Hart

-0.65

Bir

-0.65

GPU

-0.64

hawk

-0.64

odium

-0.63

POSITIVE LOGITS

 nailed

0.94

 everything

0.90

 everywhere

0.89

 boils

0.88

 summed

0.87

everything

0.85

 identical

0.83

 worthless

0.82

 sums

0.81

 unchecked

0.78

Activations Density 0.054%

phrases indicating a high degree or extent of something

expressions of generality or vagueness

No Comments

No Known Activations