INDEX

Explanations

phrases indicating potential consequences or outcomes of certain actions or events

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "cause" and its variations related to causation and effects

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

aeper

-0.70

 Quart

-0.68

 skelet

-0.68

schild

-0.68

 Technique

-0.67

atu

-0.67

ramid

-0.66

ilings

-0.64

town

-0.62

 predec

-0.62

POSITIVE LOGITS

 cele

1.03

 havoc

0.97

ãĥĨãĤ£

0.84

 irre

0.84

 headaches

0.77

 trouble

0.77

 undue

0.72

uria

0.72

 outbreaks

0.72

hift

0.71

Activations Density 0.029%

phrases indicating potential consequences or outcomes of certain actions or events

occurrences of the word "cause" and its variations related to causation and effects

No Comments

No Known Activations