INDEX

Explanations

mentions of successful outcomes or achievements

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "successful."

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

atures

-0.65

pick

-0.64

aws

-0.62

agine

-0.62

tf

-0.61

inki

-0.60

esthesia

-0.60

 Nicaragua

-0.59

Natural

-0.59

thirst

-0.58

POSITIVE LOGITS

 completion

0.86

TAIN

0.86

ullivan

0.80

 bidder

0.77

iated

0.77

iage

0.76

itude

0.73

 success

0.71

 accomplishment

0.69

 Entreprene

0.69

Activations Density 0.015%

mentions of successful outcomes or achievements

occurrences of the word "successful."

No Comments

No Known Activations