INDEX

Explanations

the name "Benedict" at varying strengths

oai_token-act-pair · gpt-3.5-turbo

references to notable individuals, particularly those in positions of power or influence

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

WAY

-0.90

WAYS

-0.90

ULT

-0.89

PER

-0.84

MIC

-0.82

BLE

-0.78

DAQ

-0.74

matically

-0.74

Ko

-0.74

matic

-0.74

POSITIVE LOGITS

 Cumber

1.05

shire

0.97

itude

0.90

 Schwarzenegger

0.85

XVI

0.85

éĹĺ

0.81

ured

0.80

ieth

0.79

sson

0.78

rophic

0.75

Activations Density 0.032%

the name "Benedict" at varying strengths

references to notable individuals, particularly those in positions of power or influence

No Comments

No Known Activations