INDEX

Explanations

minerals or materials used in construction and everyday objects

oai_token-act-pair · gpt-3.5-turbo

references to various materials, particularly metals and stones, used in construction or design

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

Kids

-0.82

onym

-0.81

angered

-0.77

Leary

-0.77

arenthood

-0.76

danger

-0.76

hoff

-0.76

OPA

-0.76

manac

-0.76

hey

-0.75

POSITIVE LOGITS

 oxide

1.10

 coffin

1.08

 alloy

1.07

 accents

1.03

 exterior

0.99

 dioxide

0.99

 fabrication

0.98

 casing

0.96

 clad

0.96

 tubing

0.95

Activations Density 0.146%

minerals or materials used in construction and everyday objects

references to various materials, particularly metals and stones, used in construction or design

No Comments

No Known Activations