INDEX

Explanations

information related to event locations and details

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

 spons

-0.87

ilater

-0.77

 laun

-0.76

ortium

-0.74

 conclud

-0.71

idden

-0.71

 authorised

-0.70

psey

-0.70

ascus

-0.70

usalem

-0.69

POSITIVE LOGITS

notations

0.82

 Dragonbound

0.80

 Subtle

0.78

sounding

0.74

(>

0.73

Medium

0.73

pants

0.72

enough

0.71

yet

0.70

Characters

0.69

Activations Density 0.148%

information related to event locations and details

No Comments

No Known Activations