INDEX

Explanations

situations related to earning recognition or rewards

oai_token-act-pair · gpt-3.5-turbo

expressions of achievement or recognition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

seek

-0.64

 Doors

-0.64

igraph

-0.63

gae

-0.62

omo

-0.61

ovo

-0.60

 processes

-0.59

anwhile

-0.58

VIDIA

-0.58

eki

-0.58

POSITIVE LOGITS

 foothold

1.19

 notoriety

1.14

 traction

0.95

 reputation

0.90

 coveted

0.89

 renown

0.87

ire

0.83

 legitimacy

0.82

 nickname

0.82

 fame

0.81

Activations Density 0.249%

situations related to earning recognition or rewards

expressions of achievement or recognition

No Comments

No Known Activations