INDEX

Explanations

references to robots or robotics

oai_token-act-pair · gpt-3.5-turbo

mentions of robots and related terms

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

WAYS

-0.78

Beg

-0.72

lv

-0.70

dn

-0.69

Ļ½

-0.68

ng

-0.68

emi

-0.68

soType

-0.67

scrib

-0.66

creen

-0.65

POSITIVE LOGITS

ically

0.95

anical

0.88

 robot

0.81

ocalypse

0.81

omach

0.80

ica

0.74

 swarm

0.73

 revolution

0.73

 overl

0.73

arm

0.72

Activations Density 0.047%

references to robots or robotics

mentions of robots and related terms

No Comments

No Known Activations