INDEX

Explanations

mentions of the name "Morrison" and related terms

oai_token-act-pair · gpt-3.5-turbo

references to specific individuals, particularly a person named Morrison

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.92

×Ķ

-0.82

×Ĳ

-0.79

lihood

-0.78

BOOK

-0.75

×ĳ

-0.67

è¯

-0.67

fare

-0.67

×Ļ

-0.67

teen

-0.65

POSITIVE LOGITS

rison

1.13

 Morrison

1.10

 Leilan

0.84

quist

0.83

ufact

0.81

inson

0.81

igon

0.80

vernment

0.77

sey

0.77

edin

0.73

Activations Density 0.005%

mentions of the name "Morrison" and related terms

references to specific individuals, particularly a person named Morrison

No Comments

No Known Activations