INDEX

Explanations

phrases related to controversial topics such as veiling, faith, and societal norms

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Siem

-0.82

hiba

-0.79

 Wolfgang

-0.78

 guiActiveUnfocused

-0.75

RBI

-0.75

 Lans

-0.73

 CrossRef

-0.73

 forecasts

-0.73

 forecast

-0.72

 Cavern

-0.71

POSITIVE LOGITS

gender

1.42

femin

1.24

sexual

1.18

marriage

1.17

rimination

1.14

LGBT

1.14

racial

1.13

 sexuality

1.13

sex

1.10

arenthood

1.08

Activations Density 0.236%

phrases related to controversial topics such as veiling, faith, and societal norms

No Comments

No Known Activations