INDEX

Explanations

questions or statements related to observing, predicting, or analyzing outcomes

oai_token-act-pair · gpt-3.5-turbo

inquiries that express curiosity or uncertainty about outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

assisted

-0.74

"}],"

-0.70

igned

-0.64

anked

-0.64

ul

-0.63

stated

-0.61

forth

-0.61

Saharan

-0.60

UTH

-0.59

åĳ

-0.59

POSITIVE LOGITS

 reaction

0.69

 trends

0.66

 reactions

0.63

 mismatch

0.63

 attrition

0.62

iasm

0.61

vine

0.61

 extent

0.61

 feasibility

0.60

 neigh

0.60

Activations Density 0.092%

questions or statements related to observing, predicting, or analyzing outcomes

inquiries that express curiosity or uncertainty about outcomes

No Comments

No Known Activations