INDEX

Explanations

terms related to achievements or accomplishments

oai_token-act-pair · gpt-3.5-turbo

terms related to achievements and accomplishments

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

odynamic

-0.81

ovy

-0.68

asus

-0.68

othes

-0.66

oxic

-0.63

odge

-0.62

©¶æ

-0.61

 Wonderland

-0.61

otiation

-0.60

osate

-0.60

POSITIVE LOGITS

 achievement

1.28

 achievements

1.26

 accomplishment

1.23

 feats

1.21

 accomplished

1.15

 accomplishments

1.14

 achie

1.09

 Achievement

1.06

 feat

1.05

 achieved

1.04

Activations Density 0.095%

terms related to achievements or accomplishments

terms related to achievements and accomplishments

No Comments

No Known Activations