INDEX

Explanations

references to a specific person named "Rand Paul."

oai_token-act-pair · gpt-3.5-turbo

mentions of a specific individual, Rand Paul

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

 dism

-0.71

 towed

-0.60

sites

-0.60

 Cyprus

-0.59

apeake

-0.58

 fertile

-0.58

 marrow

-0.57

 clutch

-0.57

 depos

-0.57

 clay

-0.57

POSITIVE LOGITS

olph

1.07

uin

1.02

wick

0.87

stad

0.84

emonium

0.81

olf

0.81

igan

0.81

entin

0.77

alf

0.75

omach

0.72

Activations Density 0.016%

references to a specific person named "Rand Paul."

mentions of a specific individual, Rand Paul

No Comments

No Known Activations