INDEX

Explanations

instances of the word "talk" and its variations indicating communication

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

 landfall

-0.78

anmar

-0.76

aples

-0.70

\/\/

-0.68

ritional

-0.67

 handc

-0.67

arte

-0.67

 unbeliev

-0.67

 conflic

-0.66

PDATE

-0.64

POSITIVE LOGITS

ership

1.16

ers

0.93

tion

0.82

 Talk

0.81

bone

0.80

edin

0.78

iba

0.77

hips

0.76

eth

0.74

about

0.74

Activations Density 0.008%

instances of the word "talk" and its variations indicating communication

No Comments

No Known Activations