INDEX

Explanations

mentions of detectives

oai_token-act-pair · gpt-3.5-turbo

mentions of detectives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

eworld

-0.90

uled

-0.83

enes

-0.82

inst

-0.79

aston

-0.79

cius

-0.79

laus

-0.79

comes

-0.77

perm

-0.77

ais

-0.76

POSITIVE LOGITS

 Detective

1.09

 detective

1.05

 Detect

0.90

 Grimoire

0.89

 Constable

0.84

 detectives

0.82

ective

0.82

 Conan

0.81

 Inspector

0.80

 Pikachu

0.76

Activations Density 0.014%

mentions of detectives

mentions of detectives

No Comments

No Known Activations