INDEX

Explanations

trigger words indicating a sequential event or action

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Following."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

imm

-0.76

adle

-0.72

immer

-0.70

inese

-0.67

agin

-0.66

access

-0.66

cci

-0.65

eri

-0.65

vere

-0.63

elo

-0.63

POSITIVE LOGITS

noon

0.81

Īè

0.73

 follows

0.71

SourceFile

0.71

teen

0.69

 Following

0.68

Following

0.65

Sym

0.65

 Steps

0.65

>:

0.64

Activations Density 0.012%

trigger words indicating a sequential event or action

instances of the word "Following."

No Comments

No Known Activations