INDEX

Explanations

terms related to trafficking

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

Pwr

-0.78

 Seym

-0.66

igans

-0.65

ATES

-0.65

 unconditional

-0.64

lists

-0.64

nuts

-0.61

FUL

-0.59

amental

-0.59

 Loll

-0.59

POSITIVE LOGITS

ffic

1.15

pped

1.12

pping

1.08

itored

1.05

aching

1.00

ached

0.98

iler

0.95

umat

0.92

ilers

0.91

asury

0.90

Activations Density 0.006%

terms related to trafficking

No Comments

No Known Activations