INDEX

Explanations

locations and technology-related terms, especially including errors or misspellings

oai_token-act-pair · gpt-3.5-turbo

specific names or terms related to locations, especially in the context of events or situations

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

cot

-0.79

ifts

-0.74

ricks

-0.72

retty

-0.71

andowski

-0.69

riot

-0.67

cair

-0.67

edient

-0.66

tz

-0.66

 Fields

-0.65

POSITIVE LOGITS

Avg

0.76

éĹĺ

0.71

BILITY

0.70

Ã±

0.69

BIL

0.69

Â¢

0.68

PsyNetMessage

0.68

acea

0.67

CVE

0.65

ventions

0.65

Activations Density 0.048%

locations and technology-related terms, especially including errors or misspellings

specific names or terms related to locations, especially in the context of events or situations

No Comments

No Known Activations