INDEX

Explanations

lists of items or activities that involve multiple entities or actions

oai_token-act-pair · gpt-3.5-turbo

conjunctions and phrases indicating connections or relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

catentry

-0.65

igate

-0.61

lace

-0.61

ube

-0.59

speaking

-0.58

quart

-0.57

mount

-0.57

detail

-0.57

 Reporting

-0.56

 Serving

-0.56

POSITIVE LOGITS

 gave

1.41

 drove

1.40

 waited

1.40

 ensured

1.35

 threw

1.33

 proceeded

1.33

 walked

1.32

 took

1.31

ran

1.31

 stayed

1.31

Activations Density 1.113%

lists of items or activities that involve multiple entities or actions

conjunctions and phrases indicating connections or relationships

No Comments

No Known Activations