INDEX

Explanations

proper nouns related to people or places, particularly those including the word "Samar"

oai_token-act-pair · gpt-3.5-turbo

references to geographical locations and associated entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

RAFT

-0.77

netflix

-0.75

nut

-0.74

puff

-0.74

rar

-0.72

rams

-0.70

spring

-0.68

bending

-0.68

oola

-0.67

ORN

-0.66

POSITIVE LOGITS

itans

1.00

 Samar

0.90

itan

0.88

pling

0.85

eness

0.72

Kou

0.71

 Strip

0.70

ãĥ£

0.69

©

0.67

µ

0.66

Activations Density 0.047%

proper nouns related to people or places, particularly those including the word "Samar"

references to geographical locations and associated entities

No Comments

No Known Activations