INDEX

Explanations

terms related to the city of Mari

oai_token-act-pair · gpt-3.5-turbo

proper nouns related to geographic locations and sports teams

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

rence

-0.94

cery

-0.86

rition

-0.85

rences

-0.85

cers

-0.77

cific

-0.77

eme

-0.74

cation

-0.73

ificantly

-0.72

pressed

-0.72

POSITIVE LOGITS

 Titans

1.08

 Mari

0.83

 Turtles

0.73

aic

0.72

Gat

0.72

 Nadu

0.70

 Walton

0.69

 torch

0.67

CCC

0.67

YC

0.67

Activations Density 0.021%

terms related to the city of Mari

proper nouns related to geographic locations and sports teams

No Comments

No Known Activations