INDEX

Explanations

sequences of words that may relate to technical documentation or programming

oai_token-act-pair · gpt-3.5-turbo

instances of unusual or fantastical creatures

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

ecided

-0.82

obbies

-0.75

isec

-0.72

arians

-0.71

 spont

-0.70

pherd

-0.69

 commute

-0.69

eryl

-0.68

 disagree

-0.65

undai

-0.65

POSITIVE LOGITS

 Bringing

0.82

 Provided

0.78

 Explicit

0.78

 Transcript

0.76

][

0.75

 Understanding

0.72

 Unlock

0.71

 Contemporary

0.71

Chapter

0.71

::::::::

0.71

Activations Density 0.020%

sequences of words that may relate to technical documentation or programming

instances of unusual or fantastical creatures

No Comments

No Known Activations