INDEX

Explanations

phrases mentioning locations or directions

oai_token-act-pair · gpt-3.5-turbo

references to geographic boundaries or borders

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

-0.70

TY

-0.70

BILITIES

-0.69

meg

-0.65

ns

-0.64

ptive

-0.63

ags

-0.61

adem

-0.60

ann

-0.60

agara

-0.59

POSITIVE LOGITS

side

0.87

wagon

0.77

flow

0.73

 wagon

0.70

wikipedia

0.68

 corridors

0.67

flows

0.67

along

0.67

erous

0.65

iously

0.65

Activations Density 0.018%

phrases mentioning locations or directions

references to geographic boundaries or borders

No Comments

No Known Activations