INDEX

Explanations

truncated phrases containing the abbreviation "SP"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "SP" along with its variations and related context

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

sbm

-0.80

taboola

-0.74

ãĥĥãĥĪ

-0.71

 behold

-0.67

hang

-0.67

omorph

-0.67

 Kurd

-0.66

emonic

-0.66

 subord

-0.64

 Wass

-0.62

POSITIVE LOGITS

EED

1.45

OIL

1.25

ORT

1.14

ONSORED

1.13

ORTS

1.13

ECT

1.03

IR

1.01

HER

0.94

ARK

0.94

ERSON

0.92

Activations Density 0.022%

truncated phrases containing the abbreviation "SP"

occurrences of the term "SP" along with its variations and related context

No Comments

No Known Activations