INDEX

Explanations

phrases related to personal connections and emotions

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "loved" in various contexts

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

SPONSORED

-0.96

arta

-0.88

arat

-0.80

illin

-0.78

interstitial

-0.78

agher

-0.76

Dispatch

-0.72

arb

-0.70

oteric

-0.70

arian

-0.68

POSITIVE LOGITS

 dearly

0.95

 loved

0.88

 uncond

0.84

 loving

0.77

 Loving

0.74

joy

0.74

 loves

0.73

nesday

0.73

ĸļ

0.70

itely

0.70

Activations Density 0.009%

phrases related to personal connections and emotions

mentions of the word "loved" in various contexts

No Comments

No Known Activations