INDEX

Explanations

terms related to catalyzing or impelling change or action

oai_token-act-pair · gpt-3.5-turbo

terms related to scapegoating and catalysts for change

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

sheet

-0.91

iere

-0.88

erer

-0.87

ensibly

-0.81

erers

-0.80

enegger

-0.80

owed

-0.78

omers

-0.77

ells

-0.74

ipation

-0.74

POSITIVE LOGITS

 Samar

0.73

=-=-=-=-

0.69

 blinded

0.69

apy

0.67

 Katrina

0.65

gdala

0.64

Â¯Â¯

0.64

 Kurd

0.63

lets

0.63

Cla

0.63

Activations Density 0.040%

terms related to catalyzing or impelling change or action

terms related to scapegoating and catalysts for change

No Comments

No Known Activations