INDEX

Explanations

words related to being filled with something, often positive like potential, good spirits, or structure

oai_token-act-pair · gpt-3.5-turbo

mentions of being "full of" various qualities or characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

NPR

-0.86

©¶æ¥µ

-0.83

wake

-0.82

DragonMagazine

-0.79

Enlarge

-0.79

Ĥİ

-0.74

ħĭ

-0.71

Dispatch

-0.71

SPONSORED

-0.70

mia

-0.69

POSITIVE LOGITS

 surprises

1.24

 contradictions

0.99

 goodies

0.98

 holes

0.94

 possibilities

0.91

 distractions

0.90

 emotion

0.86

 excuses

0.86

 caveats

0.86

 acron

0.86

Activations Density 0.098%

words related to being filled with something, often positive like potential, good spirits, or structure

mentions of being "full of" various qualities or characteristics

No Comments

No Known Activations