INDEX

Explanations

the presence of specific names or terms related to characters in gaming and pop culture

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

 relativity

-0.70

 Gael

-0.67

ENC

-0.66

Constructed

-0.63

anced

-0.61

 glim

-0.60

âĸĳâĸĳ

-0.60

ivas

-0.60

ASED

-0.59

GoldMagikarp

-0.58

POSITIVE LOGITS

dress

1.20

1.15

erness

1.02

ship

0.92

sburg

0.90

yssey

0.90

ships

0.89

hner

0.88

yss

0.87

sworth

0.87

Activations Density 0.013%

the presence of specific names or terms related to characters in gaming and pop culture

No Comments

No Known Activations