INDEX

Explanations

proper nouns or names, particularly containing the string "ork"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the substring "ork" in various contexts

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

 twilight

-0.65

 vanilla

-0.63

 vested

-0.62

 cardio

-0.61

âĸ¬âĸ¬

-0.61

 charity

-0.60

 brim

-0.59

 sclerosis

-0.59

 rendition

-0.58

 saturated

-0.58

POSITIVE LOGITS

ansas

1.10

ork

1.05

hire

1.01

ozy

0.97

osaurus

0.91

lass

0.91

lift

0.88

owski

0.88

uary

0.85

crew

0.85

Activations Density 0.007%

proper nouns or names, particularly containing the string "ork"

occurrences of the substring "ork" in various contexts

No Comments

No Known Activations