INDEX

Explanations

words related to colors and materials

oai_token-act-pair · gpt-3.5-turbo

negative connotations or descriptors related to color or material

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

 Dickinson

-0.74

 Norris

-0.74

 Confederation

-0.73

 GamerGate

-0.73

 Rica

-0.72

ulhu

-0.72

 Patron

-0.72

FML

-0.69

 Discipline

-0.68

 Fiscal

-0.67

POSITIVE LOGITS

based

1.32

shaped

1.13

themed

1.12

eyed

1.12

haired

1.12

clad

1.11

induced

1.11

covered

1.09

colored

1.09

derived

1.07

Activations Density 0.151%

words related to colors and materials

negative connotations or descriptors related to color or material

No Comments

No Known Activations