INDEX

Explanations

instances of the word "personally" and its variations

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

 Definitions

-0.76

eland

-0.66

 Mant

-0.65

period

-0.64

 Ends

-0.63

iens

-0.63

Dispatch

-0.62

 Deadline

-0.62

DAY

-0.62

ENCY

-0.62

POSITIVE LOGITS

 identifiable

1.07

 intervened

0.93

 benefited

0.92

 apologized

0.91

ised

0.91

vou

0.90

 insulted

0.89

 thanked

0.86

 offended

0.84

 owned

0.83

Activations Density 0.008%

instances of the word "personally" and its variations

No Comments

No Known Activations