INDEX

Explanations

historical dates

oai_token-act-pair · gpt-3.5-turbo

dates or years mentioned in the text

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

elong

-0.61

amins

-0.60

 genus

-0.58

atio

-0.58

 Gods

-0.57

icons

-0.56

axis

-0.56

Pad

-0.56

peat

-0.55

gpu

-0.55

POSITIVE LOGITS

 onwards

0.86

£ı

0.77

0.73

 partName

0.68

 onward

0.67

lished

0.65

 when

0.64

TAG

0.63

 sidx

0.63

when

0.63

Activations Density 0.090%

historical dates

dates or years mentioned in the text

No Comments

No Known Activations