INDEX

Explanations

terms related to various skills, such as development, job-seeking, coaching, and digital

oai_token-act-pair · gpt-3.5-turbo

references to various types of skills

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

romeda

-0.82

 Manz

-0.70

 Reloaded

-0.70

clipse

-0.69

choes

-0.66

 Wilhelm

-0.66

 Pall

-0.63

idays

-0.62

 Meier

-0.62

rarily

-0.62

POSITIVE LOGITS

cape

1.01

anooga

0.92

 training

0.89

learn

0.88

 skills

0.88

linger

0.83

chery

0.83

 proficiency

0.83

 tutor

0.82

hooting

0.80

Activations Density 0.023%

terms related to various skills, such as development, job-seeking, coaching, and digital

references to various types of skills

No Comments

No Known Activations