INDEX

Explanations

names of institutions, people, and notable events or phenomena

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

icka

-0.74

¥µ

-0.72

pherd

-0.71

olulu

-0.70

ĪĴ

-0.70

olves

-0.69

 renters

-0.68

eous

-0.68

iatus

-0.68

eric

-0.66

POSITIVE LOGITS

 Turing

0.94

 Pharmaceutical

0.86

 Britann

0.75

fer

0.68

Box

0.67

 Gingrich

0.67

 Clause

0.67

breaker

0.66

 Machines

0.66

 Test

0.66

Activations Density 0.005%

names of institutions, people, and notable events or phenomena

No Comments

No Known Activations