INDEX

Explanations

information about comparisons and descriptions within a context

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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SE

-0.66

MENTS

-0.66

 Diplom

-0.61

entials

-0.61

table

-0.61

Bas

-0.61

å½

-0.61

STE

-0.60

ten

-0.60

TAG

-0.60

POSITIVE LOGITS

 admittedly

0.97

 incidentally

0.94

 famously

0.94

 traditionally

0.93

 notoriously

0.92

 dominates

0.92

 tends

0.91

 lacks

0.89

 occupies

0.86

 historically

0.85

Activations Density 0.148%

information about comparisons and descriptions within a context

No Comments

No Known Activations