INDEX

Explanations

phrases related to recent events or actions

oai_token-act-pair · gpt-3.5-turbo

the word "just" in various contexts of time or confirmation

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 manifold

-0.64

 challeng

-0.64

 cous

-0.61

risk

-0.60

ses

-0.60

 seiz

-0.60

 necks

-0.60

amen

-0.59

ctr

-0.57

 depictions

-0.57

POSITIVE LOGITS

ifiable

1.07

ifications

1.07

ifi

0.97

if

0.93

IFIED

0.92

IFIC

0.91

ifiers

0.87

itia

0.84

ifier

0.82

iciary

0.81

Activations Density 0.094%

phrases related to recent events or actions

the word "just" in various contexts of time or confirmation

No Comments

No Known Activations