INDEX

Explanations

the word "put" in various contexts

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

 Grounds

-0.62

 stripe

-0.59

 Relations

-0.56

vine

-0.56

 succession

-0.55

 Dealer

-0.54

 Voices

-0.54

 resemblance

-0.54

 corridors

-0.54

 Mara

-0.54

POSITIVE LOGITS

tin

1.02

tering

0.99

 together

0.99

 aside

0.97

rid

0.91

rescent

0.90

 toget

0.88

tered

0.85

itialized

0.84

 forth

0.82

Activations Density 0.017%

the word "put" in various contexts

No Comments

No Known Activations