INDEX

Explanations

code snippets containing variable assignments and mathematical operations

oai_token-act-pair · gpt-3.5-turbo

occurrences of the dollar sign symbol

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Slaughter

-0.74

 Ranking

-0.72

Ò

-0.71

 Bronze

-0.71

 Flavoring

-0.71

Die

-0.69

 Bend

-0.67

 Sandwich

-0.65

 Dise

-0.65

 Boxing

-0.65

POSITIVE LOGITS

this

1.16

context

1.09

temp

1.05

location

1.04

output

1.03

args

0.99

scope

0.98

properties

0.98

target

0.98

eval

0.97

Activations Density 0.028%

code snippets containing variable assignments and mathematical operations

occurrences of the dollar sign symbol

No Comments

No Known Activations