INDEX

Explanations

medical, educational, and technical terms

oai_token-act-pair · gpt-3.5-turbo

technical terms and concepts related to theories and critiques

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

Tur

-0.57

RT

-0.57

Commerce

-0.57

ups

-0.55

baugh

-0.55

ELD

-0.54

dur

-0.53

OVER

-0.52

 remember

-0.51

ARR

-0.51

POSITIVE LOGITS

ic

2.66

ically

2.33

ical

2.31

ics

2.25

icism

2.21

icist

1.96

ICAL

1.86

ICS

1.79

IC

1.79

icity

1.74

Activations Density 0.238%

medical, educational, and technical terms

technical terms and concepts related to theories and critiques

No Comments

No Known Activations