INDEX

Explanations

phrases related to progress or advancement

oai_token-act-pair · gpt-3.5-turbo

phrases or references to a prolonged duration or significant progress

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

agents

-0.84

iances

-0.78

selves

-0.76

packages

-0.76

redients

-0.75

CB

-0.74

illions

-0.72

icks

-0.71

osponsors

-0.71

leck

-0.70

POSITIVE LOGITS

sword

1.08

itud

1.05

 overdue

1.01

 term

0.96

ago

0.95

itudinal

0.94

 lasting

0.94

 slee

0.88

 enough

0.86

 swath

0.83

Activations Density 0.039%

phrases related to progress or advancement

phrases or references to a prolonged duration or significant progress

No Comments

No Known Activations