INDEX

Explanations

references to notable people or events in a document

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

Grade

-0.70

STD

-0.67

Government

-0.67

Repeat

-0.66

Mobil

-0.65

RELATED

-0.65

Hold

-0.65

 predec

-0.63

DAQ

-0.63

Specific

-0.63

POSITIVE LOGITS

 Profile

0.83

join

0.78

 english

0.76

cin

0.70

lations

0.69

hu

0.68

roth

0.68

ragon

0.66

sd

0.66

roma

0.66

Activations Density 0.168%

references to notable people or events in a document

No Comments

No Known Activations