INDEX

Explanations

mentions of time durations, specifically focusing on years and decades

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

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

edIn

-0.65

este

-0.65

ibrary

-0.65

¬¼

-0.62

 subp

-0.61

anooga

-0.61

 Username

-0.59

Ft

-0.59

Ĥª

-0.58

Els

-0.56

POSITIVE LOGITS

0.87

0.86

iband

0.82

 someday

0.81

izons

0.80

 olds

0.80

 hereafter

0.79

glass

0.77

 unless

0.75

Activations Density 0.071%

mentions of time durations, specifically focusing on years and decades

No Comments

No Known Activations