INDEX

Explanations

phrases indicating the activation of a plan or process

oai_token-act-pair · gpt-3.5-turbo

the phrase "come into" or its variations, suggesting a focus on actions or changes occurring or beginning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

onne

-0.79

sburg

-0.78

killer

-0.77

cia

-0.67

rake

-0.66

killers

-0.63

borg

-0.61

sburgh

-0.61

 bumps

-0.60

advertisement

-0.60

POSITIVE LOGITS

 fruition

0.99

 existence

0.95

 contact

0.95

 consideration

0.88

 sharper

0.87

 play

0.87

 prominence

0.85

 conflict

0.84

 contention

0.84

 focus

0.79

Activations Density 0.043%

phrases indicating the activation of a plan or process

the phrase "come into" or its variations, suggesting a focus on actions or changes occurring or beginning

No Comments

No Known Activations