INDEX

Explanations

names and title-like terms in various contexts, potentially related to social media or activities

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.69

omorphic

-0.68

hom

-0.65

Hom

-0.60

icum

-0.57

dogs

-0.56

brid

-0.56

bom

-0.55

 cheek

-0.55

nar

-0.54

POSITIVE LOGITS

ribute

0.66

]);

0.66

Merit

0.63

ãħĭ

0.62

 SetFontSize

0.61

isoft

0.61

?????-

0.60

 Â±

0.60

%%%%

0.59

¼

0.59

Activations Density 2.165%

names and title-like terms in various contexts, potentially related to social media or activities

No Comments

No Known Activations