INDEX

Explanations

software-related terms

oai_token-act-pair · gpt-3.5-turbo

terms related to software and politics

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

holding

-0.67

udeb

-0.66

falls

-0.66

orem

-0.66

 miscarriage

-0.66

OSP

-0.62

CVE

-0.60

ubuntu

-0.60

 tenants

-0.59

RH

-0.58

POSITIVE LOGITS

ulhu

0.84

kefeller

0.74

hower

0.72

ource

0.71

uthor

0.70

 Bicycle

0.69

\":

0.68

phrine

0.68

:'

0.67

lict

0.67

Activations Density 0.336%

software-related terms

terms related to software and politics

No Comments

No Known Activations