INDEX

Explanations

adjectives ending in 'y'

oai_token-act-pair · gpt-3.5-turbo

words and fragments related to food and cooking

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

clinton

-0.67

hoff

-0.66

ught

-0.65

 Grassley

-0.61

imaru

-0.60

 Haas

-0.60

pta

-0.59

 McCl

-0.59

Klu

-0.58

bj

-0.57

POSITIVE LOGITS

ioxide

0.73

ohyd

0.71

adoes

0.67

odes

0.67

enser

0.64

ISO

0.64

opot

0.63

NECT

0.63

EEK

0.63

ãĥ©ãĥ³

0.61

Activations Density 0.350%

adjectives ending in 'y'

words and fragments related to food and cooking

No Comments

No Known Activations