INDEX

Explanations

words related to decision-making or judgment

oai_token-act-pair · gpt-3.5-turbo

nouns and concepts related to responsibilities, dilemmas, and challenges

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

poon

-0.72

vez

-0.65

Eva

-0.64

otonin

-0.63

cill

-0.59

vic

-0.58

urses

-0.58

cot

-0.58

 Prix

-0.57

GBT

-0.57

POSITIVE LOGITS

 varies

0.89

 remains

0.75

is

0.74

isn

0.73

 arises

0.72

 differs

0.71

 seemed

0.71

 hasn

0.70

 seems

0.70

 implication

0.69

Activations Density 0.347%

words related to decision-making or judgment

nouns and concepts related to responsibilities, dilemmas, and challenges

No Comments

No Known Activations