INDEX

Explanations

the word "it" 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

ndra

-0.87

avage

-0.69

alde

-0.68

amiya

-0.66

inguished

-0.64

IOR

-0.64

asting

-0.64

Staff

-0.63

arde

-0.63

ELL

-0.63

POSITIVE LOGITS

 seriously

0.93

 stride

0.93

 cues

0.89

 away

0.85

 aback

0.83

 plunge

0.81

cue

0.80

 Seriously

0.78

 easy

0.75

awa

0.75

Activations Density 0.019%

the word "it" in various contexts

No Comments

No Known Activations