INDEX

Explanations

words related to sticks

oai_token-act-pair · gpt-3.5-turbo

references to sticks or similar objects 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

 unfocusedRange

-0.95

APH

-0.81

actionDate

-0.76

ONT

-0.72

âĸ¬

-0.71

OTO

-0.71

inators

-0.70

oding

-0.68

sbm

-0.68

ãĥ´

-0.68

POSITIVE LOGITS

holder

1.01

pole

0.96

holders

0.96

handle

0.92

iness

0.88

handled

0.87

 blender

0.87

chery

0.84

 sticks

0.82

lift

0.82

Activations Density 0.013%

words related to sticks

references to sticks or similar objects in various contexts

No Comments

No Known Activations