INDEX

Explanations

continuous actions or processes described in the text

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

 manag

-0.69

cop

-0.68

=-=-

-0.64

ikers

-0.64

 kicker

-0.62

 laun

-0.60

reet

-0.60

cknowled

-0.58

ritical

-0.58

WTO

-0.58

POSITIVE LOGITS

 tonight

0.84

hani

0.80

 lately

0.75

 today

0.74

piring

0.72

soDeliveryDate

0.71

utical

0.70

Ø©

0.70

igating

0.70

edIn

0.69

Activations Density 0.071%

continuous actions or processes described in the text

No Comments

No Known Activations