INDEX

Explanations

statements about analogies and comparisons between different concepts

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

 Universities

-0.74

 Legions

-0.73

 directions

-0.68

 newsletters

-0.66

 Surve

-0.65

 Pers

-0.65

luster

-0.64

 Dems

-0.62

 Kurds

-0.61

alities

-0.61

POSITIVE LOGITS

 ALWAYS

0.87

agraph

0.81

 capable

0.78

typically

0.78

 indistinguishable

0.78

 usually

0.77

 worth

0.77

agine

0.76

 inherently

0.75

 preferable

0.74

Activations Density 0.223%

statements about analogies and comparisons between different concepts

No Comments

No Known Activations