INDEX

Explanations

phrases indicating purposes or intentions, particularly those starting with "for."

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

entimes

-0.79

zona

-0.73

hai

-0.73

hews

-0.73

sonian

-0.70

cz

-0.70

forge

-0.70

omics

-0.70

chenko

-0.69

edin

-0.68

POSITIVE LOGITS

gery

1.04

 sale

0.98

 upcoming

0.94

bidden

0.92

geries

0.91

 each

0.88

 inclusion

0.85

 hire

0.80

 purposes

0.76

ked

0.75

Activations Density 0.104%

phrases indicating purposes or intentions, particularly those starting with "for."

No Comments

No Known Activations