INDEX

Explanations

references to specific numerical values

oai_token-act-pair · gpt-3.5-turbo

numerical data or statistics related to events or occurrences

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

 multinational

-0.68

 simplicity

-0.66

 guiActive

-0.64

 turnover

-0.62

 interf

-0.62

 resonance

-0.61

 rift

-0.60

 checklist

-0.60

agall

-0.60

 misunder

-0.60

POSITIVE LOGITS

ensis

0.72

0.68

posts

0.67

orian

0.67

 CrossRef

0.67

0.66

ae

0.64

df

0.63

ajor

0.63

Activations Density 0.093%

references to specific numerical values

numerical data or statistics related to events or occurrences

No Comments

No Known Activations