INDEX

Explanations

phrases related to the concept of appropriateness

oai_token-act-pair · gpt-3.5-turbo

instances of the word "appropriate" in various 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

chet

-0.89

peak

-0.82

planes

-0.76

plane

-0.75

cipl

-0.74

stead

-0.73

bows

-0.72

ker

-0.71

glass

-0.71

hani

-0.71

POSITIVE LOGITS

tarian

0.91

 punishment

0.84

 Dragonbound

0.78

 amounts

0.78

 guiActiveUn

0.77

 responses

0.77

 circumstances

0.76

 punishments

0.75

 sized

0.74

 attire

0.73

Activations Density 0.022%

phrases related to the concept of appropriateness

instances of the word "appropriate" in various contexts

No Comments

No Known Activations