INDEX

Explanations

specific patterns of words including phrases related to physical and abstract quantities

oai_token-act-pair · gpt-3.5-turbo

phrases indicating a high level of certainty or assurance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

help

-0.65

âĢİ

-0.65

atever

-0.65

prising

-0.63

tainment

-0.62

ibliography

-0.62

 regrets

-0.61

 Helpful

-0.60

åĳ

-0.59

 congratulations

-0.58

POSITIVE LOGITS

 rarely

0.83

 wont

0.83

 seldom

0.80

 already

0.77

 scarce

0.76

 nature

0.76

 relies

0.74

 relatively

0.74

 constantly

0.73

 inception

0.73

Activations Density 0.410%

specific patterns of words including phrases related to physical and abstract quantities

phrases indicating a high level of certainty or assurance

No Comments

No Known Activations