INDEX

Explanations

terms related to specific roles or positions within a group or organization

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "Member" associated with various contexts or roles

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

ãĤ¨ãĥ«

-0.77

 torch

-0.77

sell

-0.70

 destro

-0.69

©¶æ

-0.67

iannopoulos

-0.66

ouses

-0.66

ests

-0.65

ils

-0.65

zar

-0.65

POSITIVE LOGITS

 Member

1.08

 Members

0.97

ertodd

0.96

Activity

0.89

Joined

0.86

holder

0.85

Member

0.84

 Membership

0.80

 Countries

0.72

 Login

0.72

Activations Density 0.012%

terms related to specific roles or positions within a group or organization

occurrences of the term "Member" associated with various contexts or roles

No Comments

No Known Activations