INDEX

Explanations

names related to historical figures, particularly focusing on Abraham Lincoln

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Abraham."

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

nces

-0.85

prus

-0.79

 Flavoring

-0.75

ttes

-0.72

essee

-0.72

HMS

-0.71

lla

-0.69

hift

-0.68

eq

-0.67

TOP

-0.67

POSITIVE LOGITS

 Lincoln

1.01

shire

0.98

raham

0.97

sson

0.96

son

0.93

 Abraham

0.88

sen

0.85

sburg

0.84

lisher

0.78

ode

0.77

Activations Density 0.010%

names related to historical figures, particularly focusing on Abraham Lincoln

mentions of the name "Abraham."

No Comments

No Known Activations