INDEX

Explanations

the phrases or words indicating the result or outcome of a process or action

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate causation or outcome

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

utical

-0.90

ppa

-0.81

quet

-0.74

Jar

-0.71

hazard

-0.67

mouth

-0.67

horn

-0.66

apo

-0.66

onyms

-0.66

iffe

-0.65

POSITIVE LOGITS

 sheer

0.79

 inaction

0.75

 combining

0.70

laz

0.70

 subtract

0.70

 having

0.70

 absorbing

0.69

 electing

0.69

 being

0.69

 removing

0.67

Activations Density 0.081%

the phrases or words indicating the result or outcome of a process or action

phrases that indicate causation or outcome

No Comments

No Known Activations