INDEX

Explanations

mentions of research studies and scientific findings

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

shaw

-0.73

 warr

-0.72

 dunno

-0.68

scribe

-0.67

 improves

-0.66

 violates

-0.65

 recovers

-0.64

heit

-0.64

 ends

-0.63

acy

-0.62

POSITIVE LOGITS

 recent

0.83

 recently

0.76

 unveiling

0.74

 glimps

0.73

 vividly

0.71

 Exhibit

0.70

recent

0.70

 revelations

0.69

 excerpts

0.68

 tales

0.68

Activations Density 2.648%

mentions of research studies and scientific findings

No Comments

No Known Activations