INDEX

Explanations

references to geographical locations and statistical measures

oai_token-act-pair · gpt-3.5-turbo

phrases related to health and safety in specific locations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ruary

-0.82

iasco

-0.78

 Doodle

-0.77

ãĤ´

-0.77

ayson

-0.72

ingen

-0.69

pload

-0.68

ãĥ¯

-0.66

alion

-0.65

................................

-0.65

POSITIVE LOGITS

 favorable

0.99

 conducive

0.94

 unfavorable

0.94

 abundant

0.94

 plentiful

0.92

 proximity

0.91

 favourable

0.90

 predominant

0.88

 populations

0.88

 sufficiently

0.86

Activations Density 0.480%

references to geographical locations and statistical measures

phrases related to health and safety in specific locations

No Comments

No Known Activations