INDEX

Explanations

key terms related to specific organizations or movements

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

 rune

-0.60

liest

-0.56

 downgrade

-0.53

untled

-0.53

 typo

-0.53

ieth

-0.53

::::::::

-0.52

 muted

-0.52

atican

-0.51

orthern

-0.51

POSITIVE LOGITS

folios

0.82

casters

0.79

doms

0.79

isms

0.78

atures

0.78

pieces

0.77

outs

0.77

vironments

0.77

groups

0.76

casts

0.76

Activations Density 0.466%

key terms related to specific organizations or movements

No Comments

No Known Activations