INDEX

Explanations

proper nouns and names associated with identification or recognition

oai_token-act-pair · gpt-3.5-turbo

phrases and occurrences related to identification of individuals 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 @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

issance

-0.78

idth

-0.73

ynchronous

-0.73

sei

-0.71

iths

-0.69

ights

-0.69

gard

-0.67

eries

-0.67

imeo

-0.66

istas

-0.64

POSITIVE LOGITS

rified

0.77

 surn

0.75

 identities

0.75

 identification

0.74

onyms

0.74

 landmarks

0.74

 Identification

0.73

 Identity

0.72

 Identified

0.71

 Forensic

0.71

Activations Density 0.044%

proper nouns and names associated with identification or recognition

phrases and occurrences related to identification of individuals in various contexts

No Comments

No Known Activations