INDEX

Explanations

phrases related to the concept of being filled with something

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "filled" and its related contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

hawks

-0.76

nature

-0.76

ERA

-0.69

LM

-0.67

 Appro

-0.66

Hill

-0.66

 Tackle

-0.66

CA

-0.65

appro

-0.65

rf

-0.64

POSITIVE LOGITS

 brim

0.80

 autom

0.78

 vacancies

0.74

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

0.72

ragon

0.72

acles

0.71

edin

0.71

 orbs

0.69

ummer

0.67

uper

0.66

Activations Density 0.029%

phrases related to the concept of being filled with something

occurrences of the word "filled" and its related contexts

No Comments

No Known Activations