INDEX

Explanations

strong determination or resolve

oai_token-act-pair · gpt-3.5-turbo

instances of the word "determined" 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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

umbn

-0.85

atha

-0.81

ILA

-0.76

ocular

-0.72

Ïī

-0.72

anon

-0.71

pheus

-0.69

lished

-0.69

ãģĨ

-0.68

uese

-0.67

POSITIVE LOGITS

LY

0.88

ly

0.82

lessly

0.74

ially

0.71

claw

0.68

lessness

0.67

 determination

0.66

lly

0.63

 willpower

0.61

IAL

0.61

Activations Density 0.028%

strong determination or resolve

instances of the word "determined" in various contexts

No Comments

No Known Activations