INDEX

Explanations

phrases or words related to comparisons or levels of importance

oai_token-act-pair · gpt-3.5-turbo

phrases that express a sense of increase or enhancement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

crow

-0.86

breaks

-0.82

raid

-0.81

guard

-0.81

books

-0.77

pta

-0.76

washing

-0.75

tops

-0.74

bed

-0.73

elf

-0.71

POSITIVE LOGITS

 than

1.07

 appreciation

1.03

than

0.89

 importance

0.87

 pains

0.86

 abundance

0.86

 heights

0.84

 insight

0.83

 amounts

0.82

 quantities

0.82

Activations Density 0.017%

phrases or words related to comparisons or levels of importance

phrases that express a sense of increase or enhancement

No Comments

No Known Activations