INDEX

Explanations

phrases related to explanations or justifications

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "reason" 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 @ 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

boro

-0.66

agra

-0.66

KY

-0.65

 helicop

-0.65

 likeness

-0.64

 Riders

-0.61

 needle

-0.61

oba

-0.60

inis

-0.60

NetMessage

-0.59

POSITIVE LOGITS

abl

1.01

 reasons

0.95

neum

0.89

 sake

0.80

reason

0.79

mpeg

0.75

resy

0.75

asons

0.74

 unrelated

0.72

 purposes

0.71

Activations Density 0.028%

phrases related to explanations or justifications

mentions of the word "reason" in various contexts

No Comments

No Known Activations