INDEX

Explanations

terms related to specific skills or competencies

oai_token-act-pair · gpt-3.5-turbo

nouns that represent categories or classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

oret

-0.69

bot

-0.63

GIF

-0.58

biased

-0.58

][

-0.58

luaj

-0.57

javascript

-0.56

po

-0.56

 shorts

-0.56

uristic

-0.55

POSITIVE LOGITS

 respectively

2.17

 alike

1.97

hips

1.07

depending

1.01

 simultaneously

0.95

 interchange

0.89

 collide

0.85

 depending

0.81

 concurrently

0.78

 jointly

0.76

Activations Density 0.542%

terms related to specific skills or competencies

nouns that represent categories or classifications

No Comments

No Known Activations