INDEX

Explanations

phrases related to providing help or support

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "assist" and its variations

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

place

-0.80

Pict

-0.73

bur

-0.72

nu

-0.72

peror

-0.68

ban

-0.68

meat

-0.63

prison

-0.63

club

-0.63

é¾

-0.62

POSITIVE LOGITS

 assisting

0.91

 assist

0.89

 aids

0.84

 assists

0.78

 assistance

0.77

aid

0.74

ments

0.73

 Desk

0.72

assisted

0.72

 assisted

0.71

Activations Density 0.032%

phrases related to providing help or support

occurrences of the word "assist" and its variations

No Comments

No Known Activations