INDEX

Explanations

adjectives describing the appearance or characteristics of objects or people

oai_token-act-pair · gpt-3.5-turbo

descriptions of qualities or characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

izon

-0.80

robe

-0.75

WHERE

-0.75

ESE

-0.73

asio

-0.72

 Tycoon

-0.71

ONSORED

-0.68

=(

-0.67

è£ħ

-0.67

utterstock

-0.65

POSITIVE LOGITS

 albeit

1.18

um

0.94

albeit

0.90

huh

0.82

 supra

0.82

uh

0.81

 charismatic

0.77

 unprotected

0.72

 consensual

0.71

 imaginative

0.71

Activations Density 0.107%

adjectives describing the appearance or characteristics of objects or people

descriptions of qualities or characteristics

No Comments

No Known Activations