INDEX

Explanations

phrases indicating collaboration or shared participation, often including a list of entities or individuals involved

oai_token-act-pair · gpt-3.5-turbo

the word "along" and its frequent usage 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

oric

-0.76

ptive

-0.70

nas

-0.69

TY

-0.69

ulas

-0.67

orius

-0.66

ulu

-0.66

uum

-0.65

onomy

-0.64

ns

-0.63

POSITIVE LOGITS

side

0.82

along

0.77

wagon

0.77

lihood

0.67

idth

0.66

ward

0.65

 Vest

0.65

*=-

0.65

 Rena

0.61

 Dame

0.61

Activations Density 0.018%

phrases indicating collaboration or shared participation, often including a list of entities or individuals involved

the word "along" and its frequent usage in various contexts

No Comments

No Known Activations