INDEX

Explanations

adjectives indicating the scale or intensity of an event or action

oai_token-act-pair · gpt-3.5-turbo

intensifying adjectives that denote significance or scale

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

hops

-0.97

lees

-0.89

ifles

-0.86

ernels

-0.86

ittees

-0.85

stocks

-0.84

stories

-0.84

agents

-0.83

rooms

-0.82

rollers

-0.80

POSITIVE LOGITS

 outbreak

0.95

 regimen

0.93

 dose

0.91

 eruption

0.90

 chunk

0.90

 version

0.89

 apology

0.88

 outing

0.88

 statement

0.88

 altercation

0.88

Activations Density 0.375%

adjectives indicating the scale or intensity of an event or action

intensifying adjectives that denote significance or scale

No Comments

No Known Activations