INDEX

Explanations

terms related to causing or bringing about a specific effect or state

oai_token-act-pair · gpt-3.5-turbo

terms related to induction or causes of effects

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

fman

-0.77

 Borough

-0.66

Kro

-0.64

 Coast

-0.64

halla

-0.64

lain

-0.64

 Jenner

-0.63

Ü

-0.62

sonian

-0.61

 Blessed

-0.61

POSITIVE LOGITS

 plur

1.12

uced

0.89

 analges

0.88

 apopt

0.86

 induced

0.86

 vomiting

0.86

untarily

0.85

 induce

0.84

aneous

0.84

orescence

0.82

Activations Density 0.034%

terms related to causing or bringing about a specific effect or state

terms related to induction or causes of effects

No Comments

No Known Activations