INDEX

Explanations

results or outcomes of certain actions or events

oai_token-act-pair · gpt-3.5-turbo

phrases indicating outcomes or results

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Passage

-0.77

hare

-0.69

tera

-0.68

NetMessage

-0.68

undai

-0.68

 Spur

-0.66

vette

-0.65

pe

-0.63

heed

-0.62

don

-0.61

POSITIVE LOGITS

iveness

0.92

ively

0.91

 thereof

0.84

ivity

0.83

ainer

0.71

 result

0.68

raq

0.67

ãĤ¯

0.67

ivist

0.65

ivism

0.65

Activations Density 0.039%

results or outcomes of certain actions or events

phrases indicating outcomes or results

No Comments

No Known Activations