INDEX

Explanations

terms related to admiration and respect

oai_token-act-pair · gpt-3.5-turbo

terms related to social recognition and reputation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

adra

-0.71

tein

-0.68

orio

-0.64

guyen

-0.62

ensor

-0.61

acion

-0.60

lua

-0.59

alos

-0.58

otaur

-0.56

pan

-0.55

POSITIVE LOGITS

by

0.96

By

0.83

isSpecialOrderable

0.82

 amongst

0.80

igious

0.77

 internationally

0.75

 nationally

0.75

 worldwide

0.74

 universally

0.73

 everywhere

0.73

Activations Density 0.186%

terms related to admiration and respect

terms related to social recognition and reputation

No Comments

No Known Activations