INDEX

Explanations

references to amounts remaining or needing to be accomplished

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "remaining" along with related numerical terms or quantifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

gio

-0.76

gui

-0.75

kaya

-0.69

sych

-0.69

cause

-0.67

mbol

-0.67

rection

-0.66

imaru

-0.63

 Also

-0.63

killer

-0.63

POSITIVE LOGITS

 undecided

0.90

 intact

0.87

 remnants

0.83

 remaining

0.82

 segments

0.82

 unanswered

0.81

 portions

0.80

 fractions

0.80

 sections

0.79

 remnant

0.79

Activations Density 0.043%

references to amounts remaining or needing to be accomplished

occurrences of the word "remaining" along with related numerical terms or quantifications

No Comments

No Known Activations