INDEX

Explanations

names of specific places or people

oai_token-act-pair · gpt-3.5-turbo

references to specific locations and entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

¬¼

-0.66

_>

-0.63

 metaphor

-0.59

 coughing

-0.58

taboola

-0.57

 extent

-0.57

lde

-0.56

 academ

-0.56

muc

-0.55

POSITIVE LOGITS

aline

0.89

istration

0.85

itness

0.81

vertisement

0.81

ption

0.79

andise

0.77

asio

0.76

ause

0.74

phe

0.73

vantage

0.72

Activations Density 0.084%

names of specific places or people

references to specific locations and entities

No Comments

No Known Activations