INDEX

Explanations

expressions of understanding or rationale regarding situations and attitudes

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

chin

-0.83

raviolet

-0.80

beam

-0.79

erial

-0.77

alion

-0.76

etry

-0.76

eng

-0.74

roots

-0.74

esh

-0.73

rays

-0.70

POSITIVE LOGITS

why

0.83

 Mellon

0.83

 frustration

0.76

 curiosity

0.74

 understandable

0.74

 skepticism

0.71

 frustrations

0.71

 impat

0.71

 annoyance

0.70

 altru

0.69

Activations Density 0.015%

expressions of understanding or rationale regarding situations and attitudes

No Comments

No Known Activations