INDEX

Explanations

words related to cascading or compounding effects

oai_token-act-pair · gpt-3.5-turbo

terms related to effects and consequences of actions

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

rar

-0.79

unte

-0.75

inately

-0.71

matched

-0.64

etsk

-0.64

atography

-0.64

phis

-0.64

imen

-0.64

ocal

-0.63

uns

-0.63

POSITIVE LOGITS

 ripple

1.01

 effect

1.00

Effects

0.95

 Effect

0.94

effects

0.91

 effects

0.91

 Effects

0.87

Effect

0.81

 consequences

0.80

å¥³

0.80

Activations Density 0.090%

words related to cascading or compounding effects

terms related to effects and consequences of actions

No Comments

No Known Activations