INDEX

Explanations

words related to bones

oai_token-act-pair · gpt-3.5-turbo

references to bones and skeletons

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.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

inel

-0.95

renheit

-0.89

inen

-0.82

armac

-0.74

ggles

-0.72

judicial

-0.68

sb

-0.68

ģĸ

-0.67

 Destination

-0.66

orney

-0.66

POSITIVE LOGITS

 bones

1.16

bones

1.09

 marrow

0.89

osaurs

0.85

 Bones

0.84

 fossils

0.81

ngth

0.81

 ribs

0.78

layer

0.77

bone

0.77

Activations Density 0.018%

words related to bones

references to bones and skeletons

No Comments

No Known Activations