INDEX

Explanations

triggers or causes for actions or reactions

oai_token-act-pair · gpt-3.5-turbo

phrases indicating causation or triggers for actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

à©

-0.70

aird

-0.67

sm

-0.64

rend

-0.63

 cannabinoid

-0.63

Sham

-0.60

 GEAR

-0.59

oyd

-0.58

 squared

-0.58

 antennas

-0.57

POSITIVE LOGITS

 prompt

1.08

 prompts

0.89

iration

0.88

 laughter

0.85

 warnings

0.81

 inquiries

0.80

ienced

0.80

swers

0.78

 prompting

0.78

 questioning

0.78

Activations Density 0.036%

triggers or causes for actions or reactions

phrases indicating causation or triggers for actions

No Comments

No Known Activations