INDEX

Explanations

references to "tokens" and related concepts in a technical or financial context

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

aukee

-0.70

lli

-0.69

sonian

-0.68

yer

-0.67

 Schr

-0.66

 Rove

-0.65

lla

-0.64

ECD

-0.63

================

-0.63

 Saud

-0.62

POSITIVE LOGITS

 holders

1.09

 tokens

1.01

holders

0.96

 token

0.93

 holder

0.92

izers

0.88

izer

0.84

holder

0.81

ized

0.81

omach

0.80

Activations Density 0.006%

references to "tokens" and related concepts in a technical or financial context

No Comments

No Known Activations