INDEX

Explanations

phrases indicating uncertainty or speculation

oai_token-act-pair · gpt-3.5-turbo

expressions of ambiguity or uncertainty

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

icons

-0.70

 Grac

-0.63

files

-0.61

 Wast

-0.60

berry

-0.59

amaz

-0.58

Jiu

-0.58

istries

-0.57

culosis

-0.57

istors

-0.56

POSITIVE LOGITS

Else

1.20

 else

1.09

whatever

0.84

 thereof

0.83

etc

0.80

 similar

0.78

else

0.78

abouts

0.74

 Else

0.73

 equivalent

0.72

Activations Density 0.074%

phrases indicating uncertainty or speculation

expressions of ambiguity or uncertainty

No Comments

No Known Activations