INDEX

Explanations

terms that relate to categories, roles, or identifiers within various 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cffff

-0.73

oneliness

-0.69

tnc

-0.68

pload

-0.67

qus

-0.66

oshenko

-0.65

ritical

-0.64

nir

-0.62

agate

-0.59

ravings

-0.59

POSITIVE LOGITS

iest

0.78

of

0.77

agonist

0.76

 thereof

0.75

 amongst

0.72

liest

0.69

eers

0.67

 contender

0.65

 among

0.65

 responsible

0.63

Activations Density 0.151%

terms that relate to categories, roles, or identifiers within various contexts

No Comments

No Known Activations