INDEX

Explanations

details and descriptions related to political figures and statistics

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

ãĤ©

-0.72

ucci

-0.67

 âĵĺ

-0.67

nels

-0.66

ometimes

-0.63

©¶æ

-0.62

Äĩ

-0.61

ãĥ£

-0.60

eless

-0.59

uliffe

-0.59

POSITIVE LOGITS

0.81

0.76

0.75

0.73

rounder

0.72

angled

0.72

0.71

century

0.71

Activations Density 0.129%

details and descriptions related to political figures and statistics

No Comments

No Known Activations