INDEX

Explanations

verbs followed by descriptions or details

oai_token-act-pair · gpt-3.5-turbo

instances of the word "described."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ammy

-0.66

ificial

-0.65

 purse

-0.64

iasm

-0.64

alos

-0.64

neau

-0.64

aghetti

-0.63

ffic

-0.62

ierre

-0.62

cffff

-0.62

POSITIVE LOGITS

 descriptions

0.78

urated

0.76

REDACTED

0.76

 symptoms

0.72

 aloud

0.71

Filename

0.70

urally

0.67

 markings

0.67

ounces

0.65

Obj

0.65

Activations Density 0.026%

verbs followed by descriptions or details

instances of the word "described."

No Comments

No Known Activations