INDEX

Explanations

instances where the text discusses the concept of relying on something

oai_token-act-pair · gpt-3.5-turbo

instances of the word "rely" 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

ONSORED

-0.81

©¶æ¥µ

-0.78

Cub

-0.77

DEN

-0.76

visor

-0.74

omsky

-0.74

soType

-0.72

ogun

-0.71

Cola

-0.70

okane

-0.70

POSITIVE LOGITS

 behalf

0.94

 Saturdays

0.79

 scraps

0.76

erous

0.74

 patience

0.72

 trusting

0.70

 input

0.70

 Sundays

0.70

 inputs

0.70

umbn

0.69

Activations Density 0.059%

instances where the text discusses the concept of relying on something

instances of the word "rely" and its variations

No Comments

No Known Activations