INDEX

Explanations

discussions or debates in various contexts

oai_token-act-pair · gpt-3.5-turbo

the verb "are" in various contexts, indicating a focus on collective actions or states

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

inventoryQuantity

-0.76

 belongs

-0.72

pedia

-0.68

rarily

-0.68

 occurs

-0.67

ilege

-0.66

 lasts

-0.66

 succeeds

-0.66

izable

-0.66

izes

-0.65

POSITIVE LOGITS

 willing

1.17

 eager

1.15

 aware

1.13

 afraid

1.13

 clam

1.12

 worried

1.10

 suing

1.09

 interested

1.09

 outraged

1.08

 reluctant

1.08

Activations Density 0.306%

discussions or debates in various contexts

the verb "are" in various contexts, indicating a focus on collective actions or states

No Comments

No Known Activations