INDEX

Explanations

phrases related to being emotionally or physically affected by something

oai_token-act-pair · gpt-3.5-turbo

instances of the word "struck" used in various contexts, indicating impact or significance

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

iliary

-0.74

enser

-0.74

ilon

-0.72

umption

-0.72

ORY

-0.71

omore

-0.67

adian

-0.67

ensor

-0.65

resy

-0.64

ŀ

-0.64

POSITIVE LOGITS

 striking

0.83

 resemb

0.79

 struck

0.78

tered

0.75

 strike

0.75

ters

0.74

achi

0.71

 mast

0.69

 Strikes

0.66

breakers

0.66

Activations Density 0.017%

phrases related to being emotionally or physically affected by something

instances of the word "struck" used in various contexts, indicating impact or significance

No Comments

No Known Activations