INDEX

Explanations

words related to geographic locations and scientific terms

oai_token-act-pair · gpt-3.5-turbo

specific combinations and fragments of letters that appear in various contexts within the text

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tenance

-0.81

staking

-0.79

brush

-0.78

alyst

-0.70

ORED

-0.68

FUL

-0.68

packed

-0.67

OURCE

-0.67

NetMessage

-0.65

Topics

-0.65

POSITIVE LOGITS

la

0.83

XVI

0.79

los

0.77

 Hort

0.75

Ħ¢

0.73

XII

0.73

 Deus

0.73

las

0.72

ensis

0.72

 lang

0.71

Activations Density 0.119%

words related to geographic locations and scientific terms

specific combinations and fragments of letters that appear in various contexts within the text

No Comments

No Known Activations