INDEX

Explanations

references to a specific name, likely "Lind", with numeric values attached to indicate increasing relevance

oai_token-act-pair · gpt-3.5-turbo

references to the name "Lind."

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

OPLE

-0.81

CLASSIFIED

-0.80

Ø©

-0.77

NRS

-0.71

Magikarp

-0.67

ABLE

-0.65

FTA

-0.64

SPONSORED

-0.63

 dism

-0.62

================================================================

-0.61

POSITIVE LOGITS

gren

1.21

strom

1.17

isf

1.10

enstein

1.09

holm

1.05

say

1.02

seys

1.00

stad

0.99

ahl

0.96

lasses

0.96

Activations Density 0.029%

references to a specific name, likely "Lind", with numeric values attached to indicate increasing relevance

references to the name "Lind."

No Comments

No Known Activations