INDEX

Explanations

words related to imitating or emulating

oai_token-act-pair · gpt-3.5-turbo

words related to imitation and mimicry

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

band

-0.76

endale

-0.72

uid

-0.70

Frag

-0.69

asse

-0.69

Present

-0.68

elle

-0.67

dies

-0.66

stone

-0.66

enders

-0.66

POSITIVE LOGITS

 likeness

0.96

 imitation

0.88

 emulate

0.86

 imitate

0.85

natureconservancy

0.80

iliar

0.80

ãĤ¼ãĤ¦ãĤ¹

0.69

 idol

0.68

 mock

0.67

 copyrighted

0.67

Activations Density 0.053%

words related to imitating or emulating

words related to imitation and mimicry

No Comments

No Known Activations