INDEX

Explanations

mentions of decisions or actions taken by individuals

oai_token-act-pair · gpt-3.5-turbo

instances of personal growth and transformative experiences

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

display

-0.72

ofer

-0.72

anium

-0.65

ansk

-0.64

eva

-0.64

scribe

-0.62

oshenko

-0.62

ovi

-0.61

auder

-0.61

 cone

-0.60

POSITIVE LOGITS

 eventually

0.93

 reluctantly

0.87

Eventually

0.83

 promptly

0.82

Soon

0.81

uddenly

0.81

 soon

0.79

ometime

0.75

 quickly

0.75

later

0.75

Activations Density 1.812%

mentions of decisions or actions taken by individuals

instances of personal growth and transformative experiences

No Comments

No Known Activations