INDEX

Explanations

mentions of the word "Lind" with a strong preference for an exact match on "Lind" followed by a single character

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Lind" in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

OPLE

-0.82

CLASSIFIED

-0.75

Ø©

-0.73

Magikarp

-0.67

FTA

-0.65

ABLE

-0.64

NRS

-0.64

IBLE

-0.62

 diaper

-0.61

 dism

-0.60

POSITIVE LOGITS

gren

1.18

isf

1.09

strom

1.05

say

1.04

enstein

1.03

seys

1.02

stad

0.98

holm

0.97

ahl

0.95

berg

0.95

Activations Density 0.020%

mentions of the word "Lind" with a strong preference for an exact match on "Lind" followed by a single character

mentions of the name "Lind" in various contexts

No Comments

No Known Activations