INDEX

Explanations

names of political figures and locations

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

MPG

-0.61

 soph

-0.57

 analytic

-0.54

 theoret

-0.53

oret

-0.53

 democr

-0.51

 evasion

-0.51

eatures

-0.51

 rall

-0.50

 Balk

-0.50

POSITIVE LOGITS

 whom

0.89

*.

0.79

who

0.78

$.

0.74

 respectively

0.74

Cola

0.73

who

0.72

 onto

0.70

>.

0.70

Jr

0.70

Activations Density 3.485%

names of political figures and locations

No Comments

No Known Activations