INDEX

Explanations

words related to implications

oai_token-act-pair · gpt-3.5-turbo

discussions related to the consequences or significance of findings and events

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

fighters

-0.79

few

-0.77

vez

-0.76

ves

-0.75

bows

-0.75

zig

-0.73

bones

-0.73

cop

-0.71

fighter

-0.71

ced

-0.68

POSITIVE LOGITS

 implications

1.04

 ramifications

0.92

romeda

0.90

 Impl

0.79

 fallout

0.78

afety

0.77

notations

0.77

notation

0.76

 thereof

0.76

 repercussions

0.75

Activations Density 0.034%

words related to implications

discussions related to the consequences or significance of findings and events

No Comments

No Known Activations