INDEX

Explanations

adjectives describing something as clear or easily understood

oai_token-act-pair · gpt-3.5-turbo

instances of the word "obvious."

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

ingers

-0.80

borg

-0.79

nan

-0.74

uden

-0.73

ldom

-0.71

uum

-0.71

restling

-0.70

rigan

-0.68

ntil

-0.68

icum

-0.67

POSITIVE LOGITS

iary

1.06

 culprit

0.91

 contradiction

0.84

 obvious

0.78

 annoyance

0.75

 implication

0.75

 signs

0.74

ibility

0.74

 deduction

0.73

 omission

0.73

Activations Density 0.033%

adjectives describing something as clear or easily understood

instances of the word "obvious."

No Comments

No Known Activations