INDEX

Explanations

names of individuals

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names of individuals

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

 captcha

-0.57

LEASE

-0.52

 nonviolent

-0.52

cients

-0.51

 idle

-0.51

 buzzing

-0.50

 vanishing

-0.50

').

-0.50

 thrilling

-0.49

 accomplishment

-0.48

POSITIVE LOGITS

*,

0.94

QC

0.92

0.85

!,

0.85

?,

0.84

Jr

0.79

0.77

Sr

0.77

,,

0.77

,[

0.76

Activations Density 0.199%

names of individuals

proper nouns, specifically names of individuals

No Comments

No Known Activations