INDEX

Explanations

adjectives related to proficiency or expertise

oai_token-act-pair · gpt-3.5-turbo

references to skills and expertise

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

 Manz

-0.73

 Noon

-0.71

romeda

-0.68

 Reloaded

-0.68

 paran

-0.68

 Amen

-0.68

Bom

-0.66

Wem

-0.66

 Corinthians

-0.64

 Darling

-0.64

POSITIVE LOGITS

ful

1.05

fully

1.05

learn

0.98

 proficiency

0.97

chery

0.96

training

0.93

 training

0.93

ets

0.90

et

0.90

cape

0.88

Activations Density 0.058%

adjectives related to proficiency or expertise

references to skills and expertise

No Comments

No Known Activations