INDEX

Explanations

important keywords or named entities, possibly related to news or events

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter 'K' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 heads

-0.67

 tweak

-0.64

 Adin

-0.64

 Britann

-0.63

 thousands

-0.62

 celebr

-0.62

 passages

-0.61

 hundreds

-0.61

 diapers

-0.60

 billions

-0.60

POSITIVE LOGITS

atherine

1.40

udos

1.37

eeper

1.34

laus

1.33

orea

1.32

EEP

1.30

lein

1.30

ramer

1.24

idding

1.24

avanaugh

1.24

Activations Density 0.042%

important keywords or named entities, possibly related to news or events

occurrences of the letter 'K' in various contexts

No Comments

No Known Activations