INDEX

Explanations

causal relationships or explanations involving the word "caused by"

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate causation or attribution of events or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

fal

-0.87

ark

-0.85

apest

-0.84

spect

-0.84

ura

-0.82

umat

-0.79

©¶æ¥µ

-0.76

alogue

-0.76

ires

-0.76

imensional

-0.75

POSITIVE LOGITS

 sheer

0.86

 inexper

0.82

 inaction

0.82

 differences

0.81

 factors

0.80

 deliberate

0.79

 jealousy

0.78

 inherent

0.77

 misunderstanding

0.73

 geography

0.72

Activations Density 0.171%

causal relationships or explanations involving the word "caused by"

phrases that indicate causation or attribution of events or conditions

No Comments

No Known Activations