INDEX

Explanations

possessive pronouns

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

glers

-0.73

eers

-0.72

 Meaning

-0.71

otin

-0.70

 Mermaid

-0.66

 Majority

-0.64

 Recomm

-0.63

 Unch

-0.61

 Architects

-0.60

itect

-0.60

POSITIVE LOGITS

own

1.57

 shoulders

0.91

 fingertips

0.89

self

0.87

Own

0.84

 peers

0.82

 knees

0.82

 waist

0.81

 ears

0.80

 teammates

0.80

Activations Density 0.098%

possessive pronouns

No Comments

No Known Activations