INDEX

Explanations

instances of people or objects being noticed or seen in various situations

oai_token-act-pair · gpt-3.5-turbo

instances of the word "spotted" indicating observations or sightings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

externalActionCode

-0.81

vernment

-0.79

nesia

-0.77

brance

-0.76

mort

-0.76

idem

-0.75

venge

-0.74

atever

-0.74

anwhile

-0.73

bern

-0.72

POSITIVE LOGITS

 spotted

0.92

bugs

0.91

owl

0.87

Owl

0.78

 Viper

0.76

dylib

0.74

uca

0.70

 rods

0.70

footed

0.70

lights

0.69

Activations Density 0.018%

instances of people or objects being noticed or seen in various situations

instances of the word "spotted" indicating observations or sightings

No Comments

No Known Activations