INDEX

Explanations

occurrences of pencils in different contexts

oai_token-act-pair · gpt-3.5-turbo

references to writing instruments, particularly pencils and chalk

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

worthiness

-0.72

nat

-0.72

Imm

-0.71

iety

-0.71

Fed

-0.70

Domain

-0.70

tra

-0.69

 Internal

-0.68

vm

-0.66

forces

-0.65

POSITIVE LOGITS

 pencil

4.00

pen

1.51

 chalk

1.40

 pens

1.38

ink

1.35

 scissors

1.27

 scrib

1.26

 typew

1.25

 handwriting

1.14

 notebooks

1.13

Activations Density 0.023%

occurrences of pencils in different contexts

references to writing instruments, particularly pencils and chalk

No Comments

No Known Activations