INDEX

Explanations

words related to imitating or mimicking

oai_token-act-pair · gpt-3.5-turbo

terms related to emulation, 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 @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

asse

-0.75

stone

-0.74

endale

-0.73

ker

-0.71

stones

-0.67

Frag

-0.66

view

-0.66

cloth

-0.66

elle

-0.65

seek

-0.65

POSITIVE LOGITS

 emulate

0.97

 imitate

0.85

 likeness

0.81

iliar

0.80

 imitation

0.75

 replicate

0.70

 mimic

0.69

rities

0.68

ãĤ¼ãĤ¦ãĤ¹

0.68

 mock

0.66

Activations Density 0.032%

words related to imitating or mimicking

terms related to emulation, imitation, and mimicry

No Comments

No Known Activations