INDEX

Explanations

references to elements and components in technical or scientific contexts

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

lishing

-0.84

rontal

-0.84

sburgh

-0.80

istani

-0.79

lisher

-0.77

ceed

-0.75

claimed

-0.71

zee

-0.65

ernel

-0.65

ctors

-0.64

POSITIVE LOGITS

als

0.99

ality

0.94

 elements

0.91

 element

0.89

 abund

0.81

aries

0.80

alogy

0.79

arium

0.78

ologist

0.77

ative

0.76

Activations Density 0.012%

references to elements and components in technical or scientific contexts

No Comments

No Known Activations